CINXE.COM

<!DOCTYPE html> <html > <head> <meta charset="utf-8"> <meta rel="search" type="application/opensearchdescription+xml" href="/open_search.xml" title="Academia.edu"> <meta content="width=device-width, initial-scale=1" name="viewport"> <meta name="google-site-verification" content="bKJMBZA7E43xhDOopFZkssMMkBRjvYERV-NaN4R6mrs"> <meta name="csrf-param" content="authenticity_token" /> <meta name="csrf-token" content="HGLrRoN-vHCJeJas67BVdbROfHIUTO4C-NDqM0GA7ccumGnJvm-RbUuvZRumEtF2Ol71fO8Sa4WtbOhx_42jRQ" /> <meta name="citation_title" content="An Empirical Study of Assumptions in Bayesian Optimisation" /> <meta name="citation_publication_date" content="2020/01/01" /> <meta name="citation_author" content="alexandre maraval" /> <meta name="twitter:card" content="summary" /> <meta name="twitter:url" content="https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation" /> <meta name="twitter:title" content="An Empirical Study of Assumptions in Bayesian Optimisation" /> <meta name="twitter:description" content="In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box" /> <meta name="twitter:image" content="http://a.academia-assets.com/images/twitter-card.jpeg" /> <meta property="fb:app_id" content="2369844204" /> <meta property="og:type" content="article" /> <meta property="og:url" content="https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation" /> <meta property="og:title" content="An Empirical Study of Assumptions in Bayesian Optimisation" /> <meta property="og:image" content="http://a.academia-assets.com/images/open-graph-icons/fb-paper.gif" /> <meta property="og:description" content="In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box" /> <meta property="article:author" content="https://independent.academia.edu/alexandremaraval" /> <meta name="description" content="In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box" /> <title>(PDF) An Empirical Study of Assumptions in Bayesian Optimisation</title> <link rel="canonical" href="https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation" /> <script async src="https://www.googletagmanager.com/gtag/js?id=G-5VKX33P2DS"></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'G-5VKX33P2DS', { cookie_domain: 'academia.edu', send_page_view: false, }); gtag('event', 'page_view', { 'controller': "single_work", 'action': "show", 'controller_action': 'single_work#show', 'logged_in': 'false', 'edge': 'unknown', // Send nil if there is no A/B test bucket, in case some records get logged // with missing data - that way we can distinguish between the two cases. // ab_test_bucket should be of the form <ab_test_name>:<bucket> 'ab_test_bucket': null, }) </script> <script> var $controller_name = 'single_work'; var $action_name = "show"; var $rails_env = 'production'; var $app_rev = '39bcad0772b4a9ac244d52bba0d36bb0baa6ae59'; var $domain = 'academia.edu'; var $app_host = "academia.edu"; var $asset_host = "academia-assets.com"; var $start_time = new Date().getTime(); var $recaptcha_key = "6LdxlRMTAAAAADnu_zyLhLg0YF9uACwz78shpjJB"; var $recaptcha_invisible_key = "6Lf3KHUUAAAAACggoMpmGJdQDtiyrjVlvGJ6BbAj"; var $disableClientRecordHit = false; </script> <script> window.require = { config: function() { return function() {} } } </script> <script> window.Aedu = window.Aedu || {}; window.Aedu.hit_data = null; window.Aedu.serverRenderTime = new Date(1740534032000); window.Aedu.timeDifference = new Date().getTime() - 1740534032000; </script> <script type="application/ld+json">{"@context":"https://schema.org","@type":"ScholarlyArticle","abstract":"In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input and output warping, admits exact marginal log-likelihood optimisation and is robust to the values of learned parameters. We demonstrate HEBO’s empirical efficacy on the NeurIPS 2020 Black-Box Optimisation challenge, where HEBO placed first. Upon further analysis, we observe that HEBO significantly outperforms existing black-box optimisers on 108 machine learning hyperparameter tuning tasks comprising the Bayesmark benchmark. Our findings indicate that the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, multi-objective acquisition ensembles with Pareto...","author":[{"@context":"https://schema.org","@type":"Person","name":"alexandre maraval","url":"https://independent.academia.edu/alexandremaraval"}],"contributor":[],"dateCreated":"2024-01-17","datePublished":"2020-01-01","headline":"An Empirical Study of Assumptions in Bayesian Optimisation","image":"https://attachments.academia-assets.com/110554725/thumbnails/1.jpg","inLanguage":"en","keywords":["Mathematics","Computer Science","Machine Learning","Heteroscedasticity","Bayesian Optimization","Bayesian Probability"],"publisher":{"@context":"https://schema.org","@type":"Organization","name":null},"sourceOrganization":[{"@context":"https://schema.org","@type":"EducationalOrganization","name":null}],"thumbnailUrl":"https://attachments.academia-assets.com/110554725/thumbnails/1.jpg","url":"https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation"}</script><style type="text/css">@media(max-width: 567px){:root{--token-mode: Rebrand;--dropshadow: 0 2px 4px 0 #22223340;--primary-brand: #0645b1;--error-dark: #b60000;--success-dark: #05b01c;--inactive-fill: #ebebee;--hover: #0c3b8d;--pressed: #082f75;--button-primary-fill-inactive: #ebebee;--button-primary-fill: #0645b1;--button-primary-text: #ffffff;--button-primary-fill-hover: #0c3b8d;--button-primary-fill-press: #082f75;--button-primary-icon: #ffffff;--button-primary-fill-inverse: #ffffff;--button-primary-text-inverse: #082f75;--button-primary-icon-inverse: #0645b1;--button-primary-fill-inverse-hover: #cddaef;--button-primary-stroke-inverse-pressed: #0645b1;--button-secondary-stroke-inactive: #b1b1ba;--button-secondary-fill: #eef2f9;--button-secondary-text: #082f75;--button-secondary-fill-press: #cddaef;--button-secondary-fill-inactive: #ebebee;--button-secondary-stroke: #cddaef;--button-secondary-stroke-hover: #386ac1;--button-secondary-stroke-press: #0645b1;--button-secondary-text-inactive: #b1b1ba;--button-secondary-icon: #082f75;--button-secondary-fill-hover: #e6ecf7;--button-secondary-stroke-inverse: #ffffff;--button-secondary-fill-inverse: rgba(255, 255, 255, 0);--button-secondary-icon-inverse: #ffffff;--button-secondary-icon-hover: #082f75;--button-secondary-icon-press: #082f75;--button-secondary-text-inverse: #ffffff;--button-secondary-text-hover: #082f75;--button-secondary-text-press: #082f75;--button-secondary-fill-inverse-hover: #043059;--button-xs-stroke: #141413;--button-xs-stroke-hover: #0c3b8d;--button-xs-stroke-press: #082f75;--button-xs-stroke-inactive: #ebebee;--button-xs-text: #141413;--button-xs-text-hover: #0c3b8d;--button-xs-text-press: #082f75;--button-xs-text-inactive: #91919e;--button-xs-icon: #141413;--button-xs-icon-hover: #0c3b8d;--button-xs-icon-press: #082f75;--button-xs-icon-inactive: #91919e;--button-xs-fill: #ffffff;--button-xs-fill-hover: #f4f7fc;--button-xs-fill-press: #eef2f9;--buttons-button-text-inactive: #91919e;--buttons-button-focus: #0645b1;--buttons-button-icon-inactive: #91919e;--buttons-small-buttons-corner-radius: 16px;--buttons-small-buttons-l-r-padding: 20px;--buttons-small-buttons-height: 48px;--buttons-small-buttons-gap: 8px;--buttons-small-buttons-icon-only-width: 48px;--buttons-small-buttons-icon-size: 20px;--buttons-small-buttons-stroke-default: 1px;--buttons-small-buttons-stroke-thick: 2px;--buttons-large-buttons-l-r-padding: 32px;--buttons-large-buttons-height: 64px;--buttons-large-buttons-icon-only-width: 64px;--buttons-large-buttons-icon-size: 20px;--buttons-large-buttons-gap: 8px;--buttons-large-buttons-corner-radius: 16px;--buttons-large-buttons-stroke-default: 1px;--buttons-large-buttons-stroke-thick: 2px;--buttons-extra-small-buttons-l-r-padding: 8px;--buttons-extra-small-buttons-height: 32px;--buttons-extra-small-buttons-icon-size: 16px;--buttons-extra-small-buttons-gap: 4px;--buttons-extra-small-buttons-corner-radius: 8px;--buttons-stroke-default: 1px;--buttons-stroke-thick: 2px;--background-beige: #f9f7f4;--error-light: #fff2f2;--text-placeholder: #6d6d7d;--stroke-dark: #141413;--stroke-light: #dddde2;--stroke-medium: #535366;--accent-green: #ccffd4;--accent-turquoise: #ccf7ff;--accent-yellow: #f7ffcc;--accent-peach: #ffd4cc;--accent-violet: #f7ccff;--accent-purple: #f4f7fc;--text-primary: #141413;--secondary-brand: #141413;--text-hover: #0c3b8d;--text-white: #ffffff;--text-link: #0645b1;--text-press: #082f75;--success-light: #f0f8f1;--background-light-blue: #f4f7fc;--background-white: #ffffff;--premium-dark: #877440;--premium-light: #f9f6ed;--stroke-white: #ffffff;--inactive-content: #b1b1ba;--annotate-light: #a35dff;--annotate-dark: #824acc;--grid: #eef2f9;--inactive-stroke: #ebebee;--shadow: rgba(34, 34, 51, 0.25);--text-inactive: #6d6d7d;--text-error: #b60000;--stroke-error: #b60000;--background-error: #fff2f2;--background-black: #141413;--icon-default: #141413;--icon-blue: #0645b1;--background-grey: #dddde2;--icon-grey: #b1b1ba;--text-focus: #082f75;--brand-colors-neutral-black: #141413;--brand-colors-neutral-900: #535366;--brand-colors-neutral-800: #6d6d7d;--brand-colors-neutral-700: #91919e;--brand-colors-neutral-600: #b1b1ba;--brand-colors-neutral-500: #c8c8cf;--brand-colors-neutral-400: #dddde2;--brand-colors-neutral-300: #ebebee;--brand-colors-neutral-200: #f8f8fb;--brand-colors-neutral-100: #fafafa;--brand-colors-neutral-white: #ffffff;--brand-colors-blue-900: #043059;--brand-colors-blue-800: #082f75;--brand-colors-blue-700: #0c3b8d;--brand-colors-blue-600: #0645b1;--brand-colors-blue-500: #386ac1;--brand-colors-blue-400: #cddaef;--brand-colors-blue-300: #e6ecf7;--brand-colors-blue-200: #eef2f9;--brand-colors-blue-100: #f4f7fc;--brand-colors-gold-500: #877440;--brand-colors-gold-400: #e9e3d4;--brand-colors-gold-300: #f2efe8;--brand-colors-gold-200: #f9f6ed;--brand-colors-gold-100: #f9f7f4;--brand-colors-error-900: #920000;--brand-colors-error-500: #b60000;--brand-colors-success-900: #035c0f;--brand-colors-green: #ccffd4;--brand-colors-turquoise: #ccf7ff;--brand-colors-yellow: #f7ffcc;--brand-colors-peach: #ffd4cc;--brand-colors-violet: #f7ccff;--brand-colors-error-100: #fff2f2;--brand-colors-success-500: #05b01c;--brand-colors-success-100: #f0f8f1;--text-secondary: #535366;--icon-white: #ffffff;--background-beige-darker: #f2efe8;--icon-dark-grey: #535366;--type-font-family-sans-serif: DM Sans;--type-font-family-serif: Gupter;--type-font-family-mono: IBM Plex Mono;--type-weights-300: 300;--type-weights-400: 400;--type-weights-500: 500;--type-weights-700: 700;--type-sizes-12: 12px;--type-sizes-14: 14px;--type-sizes-16: 16px;--type-sizes-18: 18px;--type-sizes-20: 20px;--type-sizes-22: 22px;--type-sizes-24: 24px;--type-sizes-28: 28px;--type-sizes-30: 30px;--type-sizes-32: 32px;--type-sizes-40: 40px;--type-sizes-42: 42px;--type-sizes-48-2: 48px;--type-line-heights-16: 16px;--type-line-heights-20: 20px;--type-line-heights-23: 23px;--type-line-heights-24: 24px;--type-line-heights-25: 25px;--type-line-heights-26: 26px;--type-line-heights-29: 29px;--type-line-heights-30: 30px;--type-line-heights-32: 32px;--type-line-heights-34: 34px;--type-line-heights-35: 35px;--type-line-heights-36: 36px;--type-line-heights-38: 38px;--type-line-heights-40: 40px;--type-line-heights-46: 46px;--type-line-heights-48: 48px;--type-line-heights-52: 52px;--type-line-heights-58: 58px;--type-line-heights-68: 68px;--type-line-heights-74: 74px;--type-line-heights-82: 82px;--type-paragraph-spacings-0: 0px;--type-paragraph-spacings-4: 4px;--type-paragraph-spacings-8: 8px;--type-paragraph-spacings-16: 16px;--type-sans-serif-xl-font-weight: 400;--type-sans-serif-xl-size: 32px;--type-sans-serif-xl-line-height: 46px;--type-sans-serif-xl-paragraph-spacing: 16px;--type-sans-serif-lg-font-weight: 400;--type-sans-serif-lg-size: 30px;--type-sans-serif-lg-line-height: 36px;--type-sans-serif-lg-paragraph-spacing: 16px;--type-sans-serif-md-font-weight: 400;--type-sans-serif-md-line-height: 30px;--type-sans-serif-md-paragraph-spacing: 16px;--type-sans-serif-md-size: 24px;--type-sans-serif-xs-font-weight: 700;--type-sans-serif-xs-line-height: 24px;--type-sans-serif-xs-paragraph-spacing: 0px;--type-sans-serif-xs-size: 18px;--type-sans-serif-sm-font-weight: 400;--type-sans-serif-sm-line-height: 32px;--type-sans-serif-sm-paragraph-spacing: 16px;--type-sans-serif-sm-size: 20px;--type-body-xl-font-weight: 400;--type-body-xl-size: 24px;--type-body-xl-line-height: 36px;--type-body-xl-paragraph-spacing: 0px;--type-body-sm-font-weight: 400;--type-body-sm-size: 14px;--type-body-sm-line-height: 20px;--type-body-sm-paragraph-spacing: 8px;--type-body-xs-font-weight: 400;--type-body-xs-size: 12px;--type-body-xs-line-height: 16px;--type-body-xs-paragraph-spacing: 0px;--type-body-md-font-weight: 400;--type-body-md-size: 16px;--type-body-md-line-height: 20px;--type-body-md-paragraph-spacing: 4px;--type-body-lg-font-weight: 400;--type-body-lg-size: 20px;--type-body-lg-line-height: 26px;--type-body-lg-paragraph-spacing: 16px;--type-body-lg-medium-font-weight: 500;--type-body-lg-medium-size: 20px;--type-body-lg-medium-line-height: 32px;--type-body-lg-medium-paragraph-spacing: 16px;--type-body-md-medium-font-weight: 500;--type-body-md-medium-size: 16px;--type-body-md-medium-line-height: 20px;--type-body-md-medium-paragraph-spacing: 4px;--type-body-sm-bold-font-weight: 700;--type-body-sm-bold-size: 14px;--type-body-sm-bold-line-height: 20px;--type-body-sm-bold-paragraph-spacing: 8px;--type-body-sm-medium-font-weight: 500;--type-body-sm-medium-size: 14px;--type-body-sm-medium-line-height: 20px;--type-body-sm-medium-paragraph-spacing: 8px;--type-serif-md-font-weight: 400;--type-serif-md-size: 32px;--type-serif-md-paragraph-spacing: 0px;--type-serif-md-line-height: 40px;--type-serif-sm-font-weight: 400;--type-serif-sm-size: 24px;--type-serif-sm-paragraph-spacing: 0px;--type-serif-sm-line-height: 26px;--type-serif-lg-font-weight: 400;--type-serif-lg-size: 48px;--type-serif-lg-paragraph-spacing: 0px;--type-serif-lg-line-height: 52px;--type-serif-xs-font-weight: 400;--type-serif-xs-size: 18px;--type-serif-xs-line-height: 24px;--type-serif-xs-paragraph-spacing: 0px;--type-serif-xl-font-weight: 400;--type-serif-xl-size: 48px;--type-serif-xl-paragraph-spacing: 0px;--type-serif-xl-line-height: 58px;--type-mono-md-font-weight: 400;--type-mono-md-size: 22px;--type-mono-md-line-height: 24px;--type-mono-md-paragraph-spacing: 0px;--type-mono-lg-font-weight: 400;--type-mono-lg-size: 40px;--type-mono-lg-line-height: 40px;--type-mono-lg-paragraph-spacing: 0px;--type-mono-sm-font-weight: 400;--type-mono-sm-size: 14px;--type-mono-sm-line-height: 24px;--type-mono-sm-paragraph-spacing: 0px;--spacing-xs-4: 4px;--spacing-xs-8: 8px;--spacing-xs-16: 16px;--spacing-sm-24: 24px;--spacing-sm-32: 32px;--spacing-md-40: 40px;--spacing-md-48: 48px;--spacing-lg-64: 64px;--spacing-lg-80: 80px;--spacing-xlg-104: 104px;--spacing-xlg-152: 152px;--spacing-xs-12: 12px;--spacing-page-section: 80px;--spacing-card-list-spacing: 48px;--spacing-text-section-spacing: 64px;--spacing-md-xs-headings: 40px;--corner-radius-radius-lg: 16px;--corner-radius-radius-sm: 4px;--corner-radius-radius-md: 8px;--corner-radius-radius-round: 104px}}@media(min-width: 568px)and (max-width: 1279px){:root{--token-mode: Rebrand;--dropshadow: 0 2px 4px 0 #22223340;--primary-brand: #0645b1;--error-dark: #b60000;--success-dark: #05b01c;--inactive-fill: #ebebee;--hover: #0c3b8d;--pressed: #082f75;--button-primary-fill-inactive: #ebebee;--button-primary-fill: #0645b1;--button-primary-text: #ffffff;--button-primary-fill-hover: #0c3b8d;--button-primary-fill-press: #082f75;--button-primary-icon: #ffffff;--button-primary-fill-inverse: #ffffff;--button-primary-text-inverse: #082f75;--button-primary-icon-inverse: #0645b1;--button-primary-fill-inverse-hover: #cddaef;--button-primary-stroke-inverse-pressed: #0645b1;--button-secondary-stroke-inactive: #b1b1ba;--button-secondary-fill: #eef2f9;--button-secondary-text: #082f75;--button-secondary-fill-press: #cddaef;--button-secondary-fill-inactive: #ebebee;--button-secondary-stroke: #cddaef;--button-secondary-stroke-hover: #386ac1;--button-secondary-stroke-press: #0645b1;--button-secondary-text-inactive: #b1b1ba;--button-secondary-icon: #082f75;--button-secondary-fill-hover: #e6ecf7;--button-secondary-stroke-inverse: #ffffff;--button-secondary-fill-inverse: rgba(255, 255, 255, 0);--button-secondary-icon-inverse: #ffffff;--button-secondary-icon-hover: #082f75;--button-secondary-icon-press: #082f75;--button-secondary-text-inverse: #ffffff;--button-secondary-text-hover: #082f75;--button-secondary-text-press: #082f75;--button-secondary-fill-inverse-hover: #043059;--button-xs-stroke: #141413;--button-xs-stroke-hover: #0c3b8d;--button-xs-stroke-press: #082f75;--button-xs-stroke-inactive: #ebebee;--button-xs-text: #141413;--button-xs-text-hover: #0c3b8d;--button-xs-text-press: #082f75;--button-xs-text-inactive: #91919e;--button-xs-icon: #141413;--button-xs-icon-hover: #0c3b8d;--button-xs-icon-press: #082f75;--button-xs-icon-inactive: #91919e;--button-xs-fill: #ffffff;--button-xs-fill-hover: #f4f7fc;--button-xs-fill-press: #eef2f9;--buttons-button-text-inactive: #91919e;--buttons-button-focus: #0645b1;--buttons-button-icon-inactive: #91919e;--buttons-small-buttons-corner-radius: 16px;--buttons-small-buttons-l-r-padding: 20px;--buttons-small-buttons-height: 48px;--buttons-small-buttons-gap: 8px;--buttons-small-buttons-icon-only-width: 48px;--buttons-small-buttons-icon-size: 20px;--buttons-small-buttons-stroke-default: 1px;--buttons-small-buttons-stroke-thick: 2px;--buttons-large-buttons-l-r-padding: 32px;--buttons-large-buttons-height: 64px;--buttons-large-buttons-icon-only-width: 64px;--buttons-large-buttons-icon-size: 20px;--buttons-large-buttons-gap: 8px;--buttons-large-buttons-corner-radius: 16px;--buttons-large-buttons-stroke-default: 1px;--buttons-large-buttons-stroke-thick: 2px;--buttons-extra-small-buttons-l-r-padding: 8px;--buttons-extra-small-buttons-height: 32px;--buttons-extra-small-buttons-icon-size: 16px;--buttons-extra-small-buttons-gap: 4px;--buttons-extra-small-buttons-corner-radius: 8px;--buttons-stroke-default: 1px;--buttons-stroke-thick: 2px;--background-beige: #f9f7f4;--error-light: #fff2f2;--text-placeholder: #6d6d7d;--stroke-dark: #141413;--stroke-light: #dddde2;--stroke-medium: #535366;--accent-green: #ccffd4;--accent-turquoise: #ccf7ff;--accent-yellow: #f7ffcc;--accent-peach: #ffd4cc;--accent-violet: #f7ccff;--accent-purple: #f4f7fc;--text-primary: #141413;--secondary-brand: #141413;--text-hover: #0c3b8d;--text-white: #ffffff;--text-link: #0645b1;--text-press: #082f75;--success-light: #f0f8f1;--background-light-blue: #f4f7fc;--background-white: #ffffff;--premium-dark: #877440;--premium-light: #f9f6ed;--stroke-white: #ffffff;--inactive-content: #b1b1ba;--annotate-light: #a35dff;--annotate-dark: #824acc;--grid: #eef2f9;--inactive-stroke: #ebebee;--shadow: rgba(34, 34, 51, 0.25);--text-inactive: #6d6d7d;--text-error: #b60000;--stroke-error: #b60000;--background-error: #fff2f2;--background-black: #141413;--icon-default: #141413;--icon-blue: #0645b1;--background-grey: #dddde2;--icon-grey: #b1b1ba;--text-focus: #082f75;--brand-colors-neutral-black: #141413;--brand-colors-neutral-900: #535366;--brand-colors-neutral-800: #6d6d7d;--brand-colors-neutral-700: #91919e;--brand-colors-neutral-600: #b1b1ba;--brand-colors-neutral-500: #c8c8cf;--brand-colors-neutral-400: #dddde2;--brand-colors-neutral-300: #ebebee;--brand-colors-neutral-200: #f8f8fb;--brand-colors-neutral-100: #fafafa;--brand-colors-neutral-white: #ffffff;--brand-colors-blue-900: #043059;--brand-colors-blue-800: #082f75;--brand-colors-blue-700: #0c3b8d;--brand-colors-blue-600: #0645b1;--brand-colors-blue-500: #386ac1;--brand-colors-blue-400: #cddaef;--brand-colors-blue-300: #e6ecf7;--brand-colors-blue-200: #eef2f9;--brand-colors-blue-100: #f4f7fc;--brand-colors-gold-500: #877440;--brand-colors-gold-400: #e9e3d4;--brand-colors-gold-300: #f2efe8;--brand-colors-gold-200: #f9f6ed;--brand-colors-gold-100: #f9f7f4;--brand-colors-error-900: #920000;--brand-colors-error-500: #b60000;--brand-colors-success-900: #035c0f;--brand-colors-green: #ccffd4;--brand-colors-turquoise: #ccf7ff;--brand-colors-yellow: #f7ffcc;--brand-colors-peach: #ffd4cc;--brand-colors-violet: #f7ccff;--brand-colors-error-100: #fff2f2;--brand-colors-success-500: #05b01c;--brand-colors-success-100: #f0f8f1;--text-secondary: #535366;--icon-white: #ffffff;--background-beige-darker: #f2efe8;--icon-dark-grey: #535366;--type-font-family-sans-serif: DM Sans;--type-font-family-serif: Gupter;--type-font-family-mono: IBM Plex Mono;--type-weights-300: 300;--type-weights-400: 400;--type-weights-500: 500;--type-weights-700: 700;--type-sizes-12: 12px;--type-sizes-14: 14px;--type-sizes-16: 16px;--type-sizes-18: 18px;--type-sizes-20: 20px;--type-sizes-22: 22px;--type-sizes-24: 24px;--type-sizes-28: 28px;--type-sizes-30: 30px;--type-sizes-32: 32px;--type-sizes-40: 40px;--type-sizes-42: 42px;--type-sizes-48-2: 48px;--type-line-heights-16: 16px;--type-line-heights-20: 20px;--type-line-heights-23: 23px;--type-line-heights-24: 24px;--type-line-heights-25: 25px;--type-line-heights-26: 26px;--type-line-heights-29: 29px;--type-line-heights-30: 30px;--type-line-heights-32: 32px;--type-line-heights-34: 34px;--type-line-heights-35: 35px;--type-line-heights-36: 36px;--type-line-heights-38: 38px;--type-line-heights-40: 40px;--type-line-heights-46: 46px;--type-line-heights-48: 48px;--type-line-heights-52: 52px;--type-line-heights-58: 58px;--type-line-heights-68: 68px;--type-line-heights-74: 74px;--type-line-heights-82: 82px;--type-paragraph-spacings-0: 0px;--type-paragraph-spacings-4: 4px;--type-paragraph-spacings-8: 8px;--type-paragraph-spacings-16: 16px;--type-sans-serif-xl-font-weight: 400;--type-sans-serif-xl-size: 42px;--type-sans-serif-xl-line-height: 46px;--type-sans-serif-xl-paragraph-spacing: 16px;--type-sans-serif-lg-font-weight: 400;--type-sans-serif-lg-size: 32px;--type-sans-serif-lg-line-height: 36px;--type-sans-serif-lg-paragraph-spacing: 16px;--type-sans-serif-md-font-weight: 400;--type-sans-serif-md-line-height: 34px;--type-sans-serif-md-paragraph-spacing: 16px;--type-sans-serif-md-size: 28px;--type-sans-serif-xs-font-weight: 700;--type-sans-serif-xs-line-height: 25px;--type-sans-serif-xs-paragraph-spacing: 0px;--type-sans-serif-xs-size: 20px;--type-sans-serif-sm-font-weight: 400;--type-sans-serif-sm-line-height: 30px;--type-sans-serif-sm-paragraph-spacing: 16px;--type-sans-serif-sm-size: 24px;--type-body-xl-font-weight: 400;--type-body-xl-size: 24px;--type-body-xl-line-height: 36px;--type-body-xl-paragraph-spacing: 0px;--type-body-sm-font-weight: 400;--type-body-sm-size: 14px;--type-body-sm-line-height: 20px;--type-body-sm-paragraph-spacing: 8px;--type-body-xs-font-weight: 400;--type-body-xs-size: 12px;--type-body-xs-line-height: 16px;--type-body-xs-paragraph-spacing: 0px;--type-body-md-font-weight: 400;--type-body-md-size: 16px;--type-body-md-line-height: 20px;--type-body-md-paragraph-spacing: 4px;--type-body-lg-font-weight: 400;--type-body-lg-size: 20px;--type-body-lg-line-height: 26px;--type-body-lg-paragraph-spacing: 16px;--type-body-lg-medium-font-weight: 500;--type-body-lg-medium-size: 20px;--type-body-lg-medium-line-height: 32px;--type-body-lg-medium-paragraph-spacing: 16px;--type-body-md-medium-font-weight: 500;--type-body-md-medium-size: 16px;--type-body-md-medium-line-height: 20px;--type-body-md-medium-paragraph-spacing: 4px;--type-body-sm-bold-font-weight: 700;--type-body-sm-bold-size: 14px;--type-body-sm-bold-line-height: 20px;--type-body-sm-bold-paragraph-spacing: 8px;--type-body-sm-medium-font-weight: 500;--type-body-sm-medium-size: 14px;--type-body-sm-medium-line-height: 20px;--type-body-sm-medium-paragraph-spacing: 8px;--type-serif-md-font-weight: 400;--type-serif-md-size: 40px;--type-serif-md-paragraph-spacing: 0px;--type-serif-md-line-height: 48px;--type-serif-sm-font-weight: 400;--type-serif-sm-size: 28px;--type-serif-sm-paragraph-spacing: 0px;--type-serif-sm-line-height: 32px;--type-serif-lg-font-weight: 400;--type-serif-lg-size: 58px;--type-serif-lg-paragraph-spacing: 0px;--type-serif-lg-line-height: 68px;--type-serif-xs-font-weight: 400;--type-serif-xs-size: 18px;--type-serif-xs-line-height: 24px;--type-serif-xs-paragraph-spacing: 0px;--type-serif-xl-font-weight: 400;--type-serif-xl-size: 74px;--type-serif-xl-paragraph-spacing: 0px;--type-serif-xl-line-height: 82px;--type-mono-md-font-weight: 400;--type-mono-md-size: 22px;--type-mono-md-line-height: 24px;--type-mono-md-paragraph-spacing: 0px;--type-mono-lg-font-weight: 400;--type-mono-lg-size: 40px;--type-mono-lg-line-height: 40px;--type-mono-lg-paragraph-spacing: 0px;--type-mono-sm-font-weight: 400;--type-mono-sm-size: 14px;--type-mono-sm-line-height: 24px;--type-mono-sm-paragraph-spacing: 0px;--spacing-xs-4: 4px;--spacing-xs-8: 8px;--spacing-xs-16: 16px;--spacing-sm-24: 24px;--spacing-sm-32: 32px;--spacing-md-40: 40px;--spacing-md-48: 48px;--spacing-lg-64: 64px;--spacing-lg-80: 80px;--spacing-xlg-104: 104px;--spacing-xlg-152: 152px;--spacing-xs-12: 12px;--spacing-page-section: 104px;--spacing-card-list-spacing: 48px;--spacing-text-section-spacing: 80px;--spacing-md-xs-headings: 40px;--corner-radius-radius-lg: 16px;--corner-radius-radius-sm: 4px;--corner-radius-radius-md: 8px;--corner-radius-radius-round: 104px}}@media(min-width: 1280px){:root{--token-mode: Rebrand;--dropshadow: 0 2px 4px 0 #22223340;--primary-brand: #0645b1;--error-dark: #b60000;--success-dark: #05b01c;--inactive-fill: #ebebee;--hover: #0c3b8d;--pressed: #082f75;--button-primary-fill-inactive: #ebebee;--button-primary-fill: #0645b1;--button-primary-text: #ffffff;--button-primary-fill-hover: #0c3b8d;--button-primary-fill-press: #082f75;--button-primary-icon: #ffffff;--button-primary-fill-inverse: #ffffff;--button-primary-text-inverse: #082f75;--button-primary-icon-inverse: #0645b1;--button-primary-fill-inverse-hover: #cddaef;--button-primary-stroke-inverse-pressed: #0645b1;--button-secondary-stroke-inactive: #b1b1ba;--button-secondary-fill: #eef2f9;--button-secondary-text: #082f75;--button-secondary-fill-press: #cddaef;--button-secondary-fill-inactive: #ebebee;--button-secondary-stroke: #cddaef;--button-secondary-stroke-hover: #386ac1;--button-secondary-stroke-press: #0645b1;--button-secondary-text-inactive: #b1b1ba;--button-secondary-icon: #082f75;--button-secondary-fill-hover: #e6ecf7;--button-secondary-stroke-inverse: #ffffff;--button-secondary-fill-inverse: rgba(255, 255, 255, 0);--button-secondary-icon-inverse: #ffffff;--button-secondary-icon-hover: #082f75;--button-secondary-icon-press: #082f75;--button-secondary-text-inverse: #ffffff;--button-secondary-text-hover: #082f75;--button-secondary-text-press: #082f75;--button-secondary-fill-inverse-hover: #043059;--button-xs-stroke: #141413;--button-xs-stroke-hover: #0c3b8d;--button-xs-stroke-press: #082f75;--button-xs-stroke-inactive: #ebebee;--button-xs-text: #141413;--button-xs-text-hover: #0c3b8d;--button-xs-text-press: #082f75;--button-xs-text-inactive: #91919e;--button-xs-icon: #141413;--button-xs-icon-hover: #0c3b8d;--button-xs-icon-press: #082f75;--button-xs-icon-inactive: #91919e;--button-xs-fill: #ffffff;--button-xs-fill-hover: #f4f7fc;--button-xs-fill-press: #eef2f9;--buttons-button-text-inactive: #91919e;--buttons-button-focus: #0645b1;--buttons-button-icon-inactive: #91919e;--buttons-small-buttons-corner-radius: 16px;--buttons-small-buttons-l-r-padding: 20px;--buttons-small-buttons-height: 48px;--buttons-small-buttons-gap: 8px;--buttons-small-buttons-icon-only-width: 48px;--buttons-small-buttons-icon-size: 20px;--buttons-small-buttons-stroke-default: 1px;--buttons-small-buttons-stroke-thick: 2px;--buttons-large-buttons-l-r-padding: 32px;--buttons-large-buttons-height: 64px;--buttons-large-buttons-icon-only-width: 64px;--buttons-large-buttons-icon-size: 20px;--buttons-large-buttons-gap: 8px;--buttons-large-buttons-corner-radius: 16px;--buttons-large-buttons-stroke-default: 1px;--buttons-large-buttons-stroke-thick: 2px;--buttons-extra-small-buttons-l-r-padding: 8px;--buttons-extra-small-buttons-height: 32px;--buttons-extra-small-buttons-icon-size: 16px;--buttons-extra-small-buttons-gap: 4px;--buttons-extra-small-buttons-corner-radius: 8px;--buttons-stroke-default: 1px;--buttons-stroke-thick: 2px;--background-beige: #f9f7f4;--error-light: #fff2f2;--text-placeholder: #6d6d7d;--stroke-dark: #141413;--stroke-light: #dddde2;--stroke-medium: #535366;--accent-green: #ccffd4;--accent-turquoise: #ccf7ff;--accent-yellow: #f7ffcc;--accent-peach: #ffd4cc;--accent-violet: #f7ccff;--accent-purple: #f4f7fc;--text-primary: #141413;--secondary-brand: #141413;--text-hover: #0c3b8d;--text-white: #ffffff;--text-link: #0645b1;--text-press: #082f75;--success-light: #f0f8f1;--background-light-blue: #f4f7fc;--background-white: #ffffff;--premium-dark: #877440;--premium-light: #f9f6ed;--stroke-white: #ffffff;--inactive-content: #b1b1ba;--annotate-light: #a35dff;--annotate-dark: #824acc;--grid: #eef2f9;--inactive-stroke: #ebebee;--shadow: rgba(34, 34, 51, 0.25);--text-inactive: #6d6d7d;--text-error: #b60000;--stroke-error: #b60000;--background-error: #fff2f2;--background-black: #141413;--icon-default: #141413;--icon-blue: #0645b1;--background-grey: #dddde2;--icon-grey: #b1b1ba;--text-focus: #082f75;--brand-colors-neutral-black: #141413;--brand-colors-neutral-900: #535366;--brand-colors-neutral-800: #6d6d7d;--brand-colors-neutral-700: #91919e;--brand-colors-neutral-600: #b1b1ba;--brand-colors-neutral-500: #c8c8cf;--brand-colors-neutral-400: #dddde2;--brand-colors-neutral-300: #ebebee;--brand-colors-neutral-200: #f8f8fb;--brand-colors-neutral-100: #fafafa;--brand-colors-neutral-white: #ffffff;--brand-colors-blue-900: #043059;--brand-colors-blue-800: #082f75;--brand-colors-blue-700: #0c3b8d;--brand-colors-blue-600: #0645b1;--brand-colors-blue-500: #386ac1;--brand-colors-blue-400: #cddaef;--brand-colors-blue-300: #e6ecf7;--brand-colors-blue-200: #eef2f9;--brand-colors-blue-100: #f4f7fc;--brand-colors-gold-500: #877440;--brand-colors-gold-400: #e9e3d4;--brand-colors-gold-300: #f2efe8;--brand-colors-gold-200: #f9f6ed;--brand-colors-gold-100: #f9f7f4;--brand-colors-error-900: #920000;--brand-colors-error-500: #b60000;--brand-colors-success-900: #035c0f;--brand-colors-green: #ccffd4;--brand-colors-turquoise: #ccf7ff;--brand-colors-yellow: #f7ffcc;--brand-colors-peach: #ffd4cc;--brand-colors-violet: #f7ccff;--brand-colors-error-100: #fff2f2;--brand-colors-success-500: #05b01c;--brand-colors-success-100: #f0f8f1;--text-secondary: #535366;--icon-white: #ffffff;--background-beige-darker: #f2efe8;--icon-dark-grey: #535366;--type-font-family-sans-serif: DM Sans;--type-font-family-serif: Gupter;--type-font-family-mono: IBM Plex Mono;--type-weights-300: 300;--type-weights-400: 400;--type-weights-500: 500;--type-weights-700: 700;--type-sizes-12: 12px;--type-sizes-14: 14px;--type-sizes-16: 16px;--type-sizes-18: 18px;--type-sizes-20: 20px;--type-sizes-22: 22px;--type-sizes-24: 24px;--type-sizes-28: 28px;--type-sizes-30: 30px;--type-sizes-32: 32px;--type-sizes-40: 40px;--type-sizes-42: 42px;--type-sizes-48-2: 48px;--type-line-heights-16: 16px;--type-line-heights-20: 20px;--type-line-heights-23: 23px;--type-line-heights-24: 24px;--type-line-heights-25: 25px;--type-line-heights-26: 26px;--type-line-heights-29: 29px;--type-line-heights-30: 30px;--type-line-heights-32: 32px;--type-line-heights-34: 34px;--type-line-heights-35: 35px;--type-line-heights-36: 36px;--type-line-heights-38: 38px;--type-line-heights-40: 40px;--type-line-heights-46: 46px;--type-line-heights-48: 48px;--type-line-heights-52: 52px;--type-line-heights-58: 58px;--type-line-heights-68: 68px;--type-line-heights-74: 74px;--type-line-heights-82: 82px;--type-paragraph-spacings-0: 0px;--type-paragraph-spacings-4: 4px;--type-paragraph-spacings-8: 8px;--type-paragraph-spacings-16: 16px;--type-sans-serif-xl-font-weight: 400;--type-sans-serif-xl-size: 42px;--type-sans-serif-xl-line-height: 46px;--type-sans-serif-xl-paragraph-spacing: 16px;--type-sans-serif-lg-font-weight: 400;--type-sans-serif-lg-size: 32px;--type-sans-serif-lg-line-height: 38px;--type-sans-serif-lg-paragraph-spacing: 16px;--type-sans-serif-md-font-weight: 400;--type-sans-serif-md-line-height: 34px;--type-sans-serif-md-paragraph-spacing: 16px;--type-sans-serif-md-size: 28px;--type-sans-serif-xs-font-weight: 700;--type-sans-serif-xs-line-height: 25px;--type-sans-serif-xs-paragraph-spacing: 0px;--type-sans-serif-xs-size: 20px;--type-sans-serif-sm-font-weight: 400;--type-sans-serif-sm-line-height: 30px;--type-sans-serif-sm-paragraph-spacing: 16px;--type-sans-serif-sm-size: 24px;--type-body-xl-font-weight: 400;--type-body-xl-size: 24px;--type-body-xl-line-height: 36px;--type-body-xl-paragraph-spacing: 0px;--type-body-sm-font-weight: 400;--type-body-sm-size: 14px;--type-body-sm-line-height: 20px;--type-body-sm-paragraph-spacing: 8px;--type-body-xs-font-weight: 400;--type-body-xs-size: 12px;--type-body-xs-line-height: 16px;--type-body-xs-paragraph-spacing: 0px;--type-body-md-font-weight: 400;--type-body-md-size: 16px;--type-body-md-line-height: 20px;--type-body-md-paragraph-spacing: 4px;--type-body-lg-font-weight: 400;--type-body-lg-size: 20px;--type-body-lg-line-height: 26px;--type-body-lg-paragraph-spacing: 16px;--type-body-lg-medium-font-weight: 500;--type-body-lg-medium-size: 20px;--type-body-lg-medium-line-height: 32px;--type-body-lg-medium-paragraph-spacing: 16px;--type-body-md-medium-font-weight: 500;--type-body-md-medium-size: 16px;--type-body-md-medium-line-height: 20px;--type-body-md-medium-paragraph-spacing: 4px;--type-body-sm-bold-font-weight: 700;--type-body-sm-bold-size: 14px;--type-body-sm-bold-line-height: 20px;--type-body-sm-bold-paragraph-spacing: 8px;--type-body-sm-medium-font-weight: 500;--type-body-sm-medium-size: 14px;--type-body-sm-medium-line-height: 20px;--type-body-sm-medium-paragraph-spacing: 8px;--type-serif-md-font-weight: 400;--type-serif-md-size: 40px;--type-serif-md-paragraph-spacing: 0px;--type-serif-md-line-height: 48px;--type-serif-sm-font-weight: 400;--type-serif-sm-size: 28px;--type-serif-sm-paragraph-spacing: 0px;--type-serif-sm-line-height: 32px;--type-serif-lg-font-weight: 400;--type-serif-lg-size: 58px;--type-serif-lg-paragraph-spacing: 0px;--type-serif-lg-line-height: 68px;--type-serif-xs-font-weight: 400;--type-serif-xs-size: 18px;--type-serif-xs-line-height: 24px;--type-serif-xs-paragraph-spacing: 0px;--type-serif-xl-font-weight: 400;--type-serif-xl-size: 74px;--type-serif-xl-paragraph-spacing: 0px;--type-serif-xl-line-height: 82px;--type-mono-md-font-weight: 400;--type-mono-md-size: 22px;--type-mono-md-line-height: 24px;--type-mono-md-paragraph-spacing: 0px;--type-mono-lg-font-weight: 400;--type-mono-lg-size: 40px;--type-mono-lg-line-height: 40px;--type-mono-lg-paragraph-spacing: 0px;--type-mono-sm-font-weight: 400;--type-mono-sm-size: 14px;--type-mono-sm-line-height: 24px;--type-mono-sm-paragraph-spacing: 0px;--spacing-xs-4: 4px;--spacing-xs-8: 8px;--spacing-xs-16: 16px;--spacing-sm-24: 24px;--spacing-sm-32: 32px;--spacing-md-40: 40px;--spacing-md-48: 48px;--spacing-lg-64: 64px;--spacing-lg-80: 80px;--spacing-xlg-104: 104px;--spacing-xlg-152: 152px;--spacing-xs-12: 12px;--spacing-page-section: 152px;--spacing-card-list-spacing: 48px;--spacing-text-section-spacing: 80px;--spacing-md-xs-headings: 40px;--corner-radius-radius-lg: 16px;--corner-radius-radius-sm: 4px;--corner-radius-radius-md: 8px;--corner-radius-radius-round: 104px}}</style><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/single_work_page/loswp-fd2fcde21889491abfafcac2e33d795c8d15f5c18207be857e53e09b77f94215.css" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system/body-170d1319f0e354621e81ca17054bb147da2856ec0702fe440a99af314a6338c5.css" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system/button-8c9ae4b5c8a2531640c354d92a1f3579c8ff103277ef74913e34c8a76d4e6c00.css" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system/heading-95367dc03b794f6737f30123738a886cf53b7a65cdef98a922a98591d60063e3.css" /><link rel="stylesheet" media="all" href="//a.academia-assets.com/assets/design_system/text_button-d1941ab08e91e29ee143084c4749da4aaffa350a2ac6eec2306b1d7a352d911a.css" /><link crossorigin="" href="https://fonts.gstatic.com/" rel="preconnect" /><link href="https://fonts.googleapis.com/css2?family=DM+Sans:ital,opsz,wght@0,9..40,100..1000;1,9..40,100..1000&family=Gupter:wght@400;500;700&family=IBM+Plex+Mono:wght@300;400&family=Material+Symbols+Outlined:opsz,wght,FILL,GRAD@20,400,0,0&display=swap" rel="stylesheet" /> </head> <body> <div id='react-modal'></div> <div class="js-upgrade-ie-banner" style="display: none; text-align: center; padding: 8px 0; background-color: #ebe480;"><p style="color: #000; font-size: 12px; margin: 0 0 4px;">Academia.edu no longer supports Internet Explorer.</p><p style="color: #000; font-size: 12px; margin: 0;">To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to <a href="https://www.academia.edu/upgrade-browser">upgrade your browser</a>.</p></div><script>// Show this banner for all versions of IE if (!!window.MSInputMethodContext || /(MSIE)/.test(navigator.userAgent)) { document.querySelector('.js-upgrade-ie-banner').style.display = 'block'; }</script> <div class="bootstrap login"><div class="modal fade login-modal" id="login-modal"><div class="login-modal-dialog modal-dialog"><div class="modal-content"><div class="modal-header"><button class="close close" data-dismiss="modal" type="button"><span aria-hidden="true">×</span><span class="sr-only">Close</span></button><h4 class="modal-title text-center"><strong>Log In</strong></h4></div><div class="modal-body"><div class="row"><div class="col-xs-10 col-xs-offset-1"><button class="btn btn-fb btn-lg btn-block btn-v-center-content" id="login-facebook-oauth-button"><svg style="float: left; width: 19px; line-height: 1em; margin-right: .3em;" aria-hidden="true" focusable="false" data-prefix="fab" data-icon="facebook-square" class="svg-inline--fa fa-facebook-square fa-w-14" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path fill="currentColor" d="M400 32H48A48 48 0 0 0 0 80v352a48 48 0 0 0 48 48h137.25V327.69h-63V256h63v-54.64c0-62.15 37-96.48 93.67-96.48 27.14 0 55.52 4.84 55.52 4.84v61h-31.27c-30.81 0-40.42 19.12-40.42 38.73V256h68.78l-11 71.69h-57.78V480H400a48 48 0 0 0 48-48V80a48 48 0 0 0-48-48z"></path></svg><small><strong>Log in</strong> with <strong>Facebook</strong></small></button><br /><button class="btn btn-google btn-lg btn-block btn-v-center-content" id="login-google-oauth-button"><svg style="float: left; width: 22px; line-height: 1em; margin-right: .3em;" aria-hidden="true" focusable="false" data-prefix="fab" data-icon="google-plus" class="svg-inline--fa fa-google-plus fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M256,8C119.1,8,8,119.1,8,256S119.1,504,256,504,504,392.9,504,256,392.9,8,256,8ZM185.3,380a124,124,0,0,1,0-248c31.3,0,60.1,11,83,32.3l-33.6,32.6c-13.2-12.9-31.3-19.1-49.4-19.1-42.9,0-77.2,35.5-77.2,78.1S142.3,334,185.3,334c32.6,0,64.9-19.1,70.1-53.3H185.3V238.1H302.2a109.2,109.2,0,0,1,1.9,20.7c0,70.8-47.5,121.2-118.8,121.2ZM415.5,273.8v35.5H380V273.8H344.5V238.3H380V202.8h35.5v35.5h35.2v35.5Z"></path></svg><small><strong>Log in</strong> with <strong>Google</strong></small></button><br /><style type="text/css">.sign-in-with-apple-button { width: 100%; height: 52px; border-radius: 3px; border: 1px solid black; cursor: pointer; } .sign-in-with-apple-button > div { margin: 0 auto; / This centers the Apple-rendered button horizontally }</style><script src="https://appleid.cdn-apple.com/appleauth/static/jsapi/appleid/1/en_US/appleid.auth.js" type="text/javascript"></script><div class="sign-in-with-apple-button" data-border="false" data-color="white" id="appleid-signin"><span   ="Sign Up with Apple" class="u-fs11"></span></div><script>AppleID.auth.init({ clientId: 'edu.academia.applesignon', scope: 'name email', redirectURI: 'https://www.academia.edu/sessions', state: "e7d3c1502c65499f6bcf5843dadcb563fa4b92f4cf7e6673837f5b02c48127a9", });</script><script>// Hacky way of checking if on fast loswp if (window.loswp == null) { (function() { const Google = window?.Aedu?.Auth?.OauthButton?.Login?.Google; const Facebook = window?.Aedu?.Auth?.OauthButton?.Login?.Facebook; if (Google) { new Google({ el: '#login-google-oauth-button', rememberMeCheckboxId: 'remember_me', track: null }); } if (Facebook) { new Facebook({ el: '#login-facebook-oauth-button', rememberMeCheckboxId: 'remember_me', track: null }); } })(); }</script></div></div></div><div class="modal-body"><div class="row"><div class="col-xs-10 col-xs-offset-1"><div class="hr-heading login-hr-heading"><span class="hr-heading-text">or</span></div></div></div></div><div class="modal-body"><div class="row"><div class="col-xs-10 col-xs-offset-1"><form class="js-login-form" action="https://www.academia.edu/sessions" accept-charset="UTF-8" method="post"><input type="hidden" name="authenticity_token" value="h3ovtWx_3AMrY6mXQ_Es8W_HkYbZqqagJVIHuwAwTx61gK06UW7xHum0WiAOU6jy4dcYiCL0Iydw7gX5vj0BnA" autocomplete="off" /><div class="form-group"><label class="control-label" for="login-modal-email-input" style="font-size: 14px;">Email</label><input class="form-control" id="login-modal-email-input" name="login" type="email" /></div><div class="form-group"><label class="control-label" for="login-modal-password-input" style="font-size: 14px;">Password</label><input class="form-control" id="login-modal-password-input" name="password" type="password" /></div><input type="hidden" name="post_login_redirect_url" id="post_login_redirect_url" value="https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation" autocomplete="off" /><div class="checkbox"><label><input type="checkbox" name="remember_me" id="remember_me" value="1" checked="checked" /><small style="font-size: 12px; margin-top: 2px; display: inline-block;">Remember me on this computer</small></label></div><br><input type="submit" name="commit" value="Log In" class="btn btn-primary btn-block btn-lg js-login-submit" data-disable-with="Log In" /></br></form><script>typeof window?.Aedu?.recaptchaManagedForm === 'function' && window.Aedu.recaptchaManagedForm( document.querySelector('.js-login-form'), document.querySelector('.js-login-submit') );</script><small style="font-size: 12px;"><br />or <a data-target="#login-modal-reset-password-container" data-toggle="collapse" href="javascript:void(0)">reset password</a></small><div class="collapse" id="login-modal-reset-password-container"><br /><div class="well margin-0x"><form class="js-password-reset-form" action="https://www.academia.edu/reset_password" accept-charset="UTF-8" method="post"><input type="hidden" name="authenticity_token" value="tRDpxH2E-ycZ5Rti1o4YPaZ87sLZJ-KM5PYOcZYLhSKH6mtLQJXWOtsy6NWbLJw-KGxnzCJ5ZwuxSgwzKAbLoA" autocomplete="off" /><p>Enter the email address you signed up with and we'll email you a reset link.</p><div class="form-group"><input class="form-control" name="email" type="email" /></div><input class="btn btn-primary btn-block g-recaptcha js-password-reset-submit" data-sitekey="6Lf3KHUUAAAAACggoMpmGJdQDtiyrjVlvGJ6BbAj" type="submit" value="Email me a link" /></form></div></div><script> require.config({ waitSeconds: 90 })(["https://a.academia-assets.com/assets/collapse-45805421cf446ca5adf7aaa1935b08a3a8d1d9a6cc5d91a62a2a3a00b20b3e6a.js"], function() { // from javascript_helper.rb $("#login-modal-reset-password-container").on("shown.bs.collapse", function() { $(this).find("input[type=email]").focus(); }); }); </script> </div></div></div><div class="modal-footer"><div class="text-center"><small style="font-size: 12px;">Need an account? <a rel="nofollow" href="https://www.academia.edu/signup">Click here to sign up</a></small></div></div></div></div></div></div><script>// If we are on subdomain or non-bootstrapped page, redirect to login page instead of showing modal (function(){ if (typeof $ === 'undefined') return; var host = window.location.hostname; if ((host === $domain || host === "www."+$domain) && (typeof $().modal === 'function')) { $("#nav_log_in").click(function(e) { // Don't follow the link and open the modal e.preventDefault(); $("#login-modal").on('shown.bs.modal', function() { $(this).find("#login-modal-email-input").focus() }).modal('show'); }); } })()</script> <div id="fb-root"></div><script>window.fbAsyncInit = function() { FB.init({ appId: "2369844204", version: "v8.0", status: true, cookie: true, xfbml: true }); // Additional initialization code. if (window.InitFacebook) { // facebook.ts already loaded, set it up. window.InitFacebook(); } else { // Set a flag for facebook.ts to find when it loads. window.academiaAuthReadyFacebook = true; } };</script> <div id="google-root"></div><script>window.loadGoogle = function() { if (window.InitGoogle) { // google.ts already loaded, set it up. window.InitGoogle("331998490334-rsn3chp12mbkiqhl6e7lu2q0mlbu0f1b"); } else { // Set a flag for google.ts to use when it loads. window.GoogleClientID = "331998490334-rsn3chp12mbkiqhl6e7lu2q0mlbu0f1b"; } };</script> <div class="header--container" id="main-header-container"><div class="header--inner-container header--inner-container-ds2"><div class="header-ds2--left-wrapper"><div class="header-ds2--left-wrapper-inner"><a data-main-header-link-target="logo_home" href="https://www.academia.edu/"><img class="hide-on-desktop-redesign" style="height: 24px; width: 24px;" alt="Academia.edu" src="//a.academia-assets.com/images/academia-logo-redesign-2015-A.svg" width="24" height="24" /><img width="145.2" height="18" class="hide-on-mobile-redesign" style="height: 24px;" alt="Academia.edu" src="//a.academia-assets.com/images/academia-logo-redesign-2015.svg" /></a><div class="header--search-container header--search-container-ds2"><form class="js-SiteSearch-form select2-no-default-pills" action="https://www.academia.edu/search" accept-charset="UTF-8" method="get"><svg style="width: 14px; height: 14px;" aria-hidden="true" focusable="false" data-prefix="fas" data-icon="search" class="header--search-icon svg-inline--fa fa-search fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M505 442.7L405.3 343c-4.5-4.5-10.6-7-17-7H372c27.6-35.3 44-79.7 44-128C416 93.1 322.9 0 208 0S0 93.1 0 208s93.1 208 208 208c48.3 0 92.7-16.4 128-44v16.3c0 6.4 2.5 12.5 7 17l99.7 99.7c9.4 9.4 24.6 9.4 33.9 0l28.3-28.3c9.4-9.4 9.4-24.6.1-34zM208 336c-70.7 0-128-57.2-128-128 0-70.7 57.2-128 128-128 70.7 0 128 57.2 128 128 0 70.7-57.2 128-128 128z"></path></svg><input class="header--search-input header--search-input-ds2 js-SiteSearch-form-input" data-main-header-click-target="search_input" name="q" placeholder="Search" type="text" /></form></div></div></div><nav class="header--nav-buttons header--nav-buttons-ds2 js-main-nav"><button class="ds2-5-button ds2-5-button--secondary js-header-login-url header-button-ds2 header-login-ds2 hide-on-mobile-redesign react-login-modal-opener" data-signup-modal="{"location":"login-button--header"}" rel="nofollow">Log In</button><button class="ds2-5-button ds2-5-button--secondary header-button-ds2 hide-on-mobile-redesign react-login-modal-opener" data-signup-modal="{"location":"signup-button--header"}" rel="nofollow">Sign Up</button><button class="header--hamburger-button header--hamburger-button-ds2 hide-on-desktop-redesign js-header-hamburger-button"><div class="icon-bar"></div><div class="icon-bar" style="margin-top: 4px;"></div><div class="icon-bar" style="margin-top: 4px;"></div></button></nav></div><ul class="header--dropdown-container js-header-dropdown"><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/login" rel="nofollow">Log In</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/signup" rel="nofollow">Sign Up</a></li><li class="header--dropdown-row js-header-dropdown-expand-button"><button class="header--dropdown-button">more<svg aria-hidden="true" focusable="false" data-prefix="fas" data-icon="caret-down" class="header--dropdown-button-icon svg-inline--fa fa-caret-down fa-w-10" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 320 512"><path fill="currentColor" d="M31.3 192h257.3c17.8 0 26.7 21.5 14.1 34.1L174.1 354.8c-7.8 7.8-20.5 7.8-28.3 0L17.2 226.1C4.6 213.5 13.5 192 31.3 192z"></path></svg></button></li><li><ul class="header--expanded-dropdown-container"><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/about">About</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/press">Press</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/documents">Papers</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/terms">Terms</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/privacy">Privacy</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/copyright">Copyright</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://www.academia.edu/hiring"><svg aria-hidden="true" focusable="false" data-prefix="fas" data-icon="briefcase" class="header--dropdown-row-icon svg-inline--fa fa-briefcase fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M320 336c0 8.84-7.16 16-16 16h-96c-8.84 0-16-7.16-16-16v-48H0v144c0 25.6 22.4 48 48 48h416c25.6 0 48-22.4 48-48V288H320v48zm144-208h-80V80c0-25.6-22.4-48-48-48H176c-25.6 0-48 22.4-48 48v48H48c-25.6 0-48 22.4-48 48v80h512v-80c0-25.6-22.4-48-48-48zm-144 0H192V96h128v32z"></path></svg>We're Hiring!</a></li><li class="header--dropdown-row"><a class="header--dropdown-link" href="https://support.academia.edu/hc/en-us"><svg aria-hidden="true" focusable="false" data-prefix="fas" data-icon="question-circle" class="header--dropdown-row-icon svg-inline--fa fa-question-circle fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M504 256c0 136.997-111.043 248-248 248S8 392.997 8 256C8 119.083 119.043 8 256 8s248 111.083 248 248zM262.655 90c-54.497 0-89.255 22.957-116.549 63.758-3.536 5.286-2.353 12.415 2.715 16.258l34.699 26.31c5.205 3.947 12.621 3.008 16.665-2.122 17.864-22.658 30.113-35.797 57.303-35.797 20.429 0 45.698 13.148 45.698 32.958 0 14.976-12.363 22.667-32.534 33.976C247.128 238.528 216 254.941 216 296v4c0 6.627 5.373 12 12 12h56c6.627 0 12-5.373 12-12v-1.333c0-28.462 83.186-29.647 83.186-106.667 0-58.002-60.165-102-116.531-102zM256 338c-25.365 0-46 20.635-46 46 0 25.364 20.635 46 46 46s46-20.636 46-46c0-25.365-20.635-46-46-46z"></path></svg>Help Center</a></li><li class="header--dropdown-row js-header-dropdown-collapse-button"><button class="header--dropdown-button">less<svg aria-hidden="true" focusable="false" data-prefix="fas" data-icon="caret-up" class="header--dropdown-button-icon svg-inline--fa fa-caret-up fa-w-10" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 320 512"><path fill="currentColor" d="M288.662 352H31.338c-17.818 0-26.741-21.543-14.142-34.142l128.662-128.662c7.81-7.81 20.474-7.81 28.284 0l128.662 128.662c12.6 12.599 3.676 34.142-14.142 34.142z"></path></svg></button></li></ul></li></ul></div> <script src="//a.academia-assets.com/assets/webpack_bundles/fast_loswp-bundle-6d6bc049d6168e818bc2e4b18a4599d82634a88356d03b516a88e8508f5405d3.js" defer="defer"></script><script>window.loswp = {}; window.loswp.author = 67755877; window.loswp.bulkDownloadFilterCounts = {}; window.loswp.hasDownloadableAttachment = true; window.loswp.hasViewableAttachments = true; // TODO: just use routes for this window.loswp.loginUrl = "https://www.academia.edu/login?post_login_redirect_url=https%3A%2F%2Fwww.academia.edu%2F113649419%2FAn_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation%3Fauto%3Ddownload"; window.loswp.translateUrl = "https://www.academia.edu/login?post_login_redirect_url=https%3A%2F%2Fwww.academia.edu%2F113649419%2FAn_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation%3Fshow_translation%3Dtrue"; window.loswp.previewableAttachments = [{"id":110554725,"identifier":"Attachment_110554725","shouldShowBulkDownload":false}]; window.loswp.shouldDetectTimezone = true; window.loswp.shouldShowBulkDownload = true; window.loswp.showSignupCaptcha = false window.loswp.willEdgeCache = false; window.loswp.work = {"work":{"id":113649419,"created_at":"2024-01-17T10:09:12.512-08:00","from_world_paper_id":248363267,"updated_at":"2024-01-17T11:25:01.914-08:00","_data":{"abstract":"In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input and output warping, admits exact marginal log-likelihood optimisation and is robust to the values of learned parameters. We demonstrate HEBO’s empirical efficacy on the NeurIPS 2020 Black-Box Optimisation challenge, where HEBO placed first. Upon further analysis, we observe that HEBO significantly outperforms existing black-box optimisers on 108 machine learning hyperparameter tuning tasks comprising the Bayesmark benchmark. Our findings indicate that the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, multi-objective acquisition ensembles with Pareto...","publication_date":"2020,,"},"document_type":"paper","pre_hit_view_count_baseline":null,"quality":"high","language":"en","title":"An Empirical Study of Assumptions in Bayesian Optimisation","broadcastable":false,"draft":null,"has_indexable_attachment":true,"indexable":true}}["work"]; window.loswp.workCoauthors = [67755877]; window.loswp.locale = "en"; window.loswp.countryCode = "SG"; window.loswp.cwvAbTestBucket = ""; window.loswp.designVariant = "ds_vanilla"; window.loswp.fullPageMobileSutdModalVariant = "full_page_mobile_sutd_modal"; window.loswp.useOptimizedScribd4genScript = false; window.loginModal = {}; window.loginModal.appleClientId = 'edu.academia.applesignon'; window.userInChina = "false";</script><script defer="" src="https://accounts.google.com/gsi/client"></script><div class="ds-loswp-container"><div class="ds-work-card--grid-container"><div class="ds-work-card--container js-loswp-work-card"><div class="ds-work-card--cover"><div class="ds-work-cover--wrapper"><div class="ds-work-cover--container"><button class="ds-work-cover--clickable js-swp-download-button" data-signup-modal="{"location":"swp-splash-paper-cover","attachmentId":110554725,"attachmentType":"pdf"}"><img alt="First page of “An Empirical Study of Assumptions in Bayesian Optimisation”" class="ds-work-cover--cover-thumbnail" src="https://0.academia-photos.com/attachment_thumbnails/110554725/mini_magick20240117-1-ejc6wz.png?1705518303" /><img alt="PDF Icon" class="ds-work-cover--file-icon" src="//a.academia-assets.com/images/single_work_splash/adobe_icon.svg" /><div class="ds-work-cover--hover-container"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">download</span><p>Download Free PDF</p></div><div class="ds-work-cover--ribbon-container">Download Free PDF</div><div class="ds-work-cover--ribbon-triangle"></div></button></div></div></div><div class="ds-work-card--work-information"><h1 class="ds-work-card--work-title">An Empirical Study of Assumptions in Bayesian Optimisation</h1><div class="ds-work-card--work-authors ds-work-card--detail"><a class="ds-work-card--author js-wsj-grid-card-author ds2-5-body-md ds2-5-body-link" data-author-id="67755877" href="https://independent.academia.edu/alexandremaraval"><img alt="Profile image of alexandre maraval" class="ds-work-card--author-avatar" src="//a.academia-assets.com/images/s65_no_pic.png" />alexandre maraval</a></div><div class="ds-work-card--detail"><p class="ds-work-card--detail ds2-5-body-sm">2020</p><div class="ds-work-card--work-metadata"><div class="ds-work-card--work-metadata__stat"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">visibility</span><p class="ds2-5-body-sm" id="work-metadata-view-count">…</p></div><div class="ds-work-card--work-metadata__stat"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">description</span><p class="ds2-5-body-sm">80 pages</p></div><div class="ds-work-card--work-metadata__stat"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">link</span><p class="ds2-5-body-sm">1 file</p></div></div><script>(async () => { const workId = 113649419; const worksViewsPath = "/v0/works/views?subdomain_param=api&work_ids%5B%5D=113649419"; const getWorkViews = async (workId) => { const response = await fetch(worksViewsPath); if (!response.ok) { throw new Error('Failed to load work views'); } const data = await response.json(); return data.views[workId]; }; // Get the view count for the work - we send this immediately rather than waiting for // the DOM to load, so it can be available as soon as possible (but without holding up // the backend or other resource requests, because it's a bit expensive and not critical). const viewCount = await getWorkViews(workId); const updateViewCount = (viewCount) => { try { const viewCountNumber = parseInt(viewCount, 10); if (viewCountNumber === 0) { // Remove the whole views element if there are zero views. document.getElementById('work-metadata-view-count')?.parentNode?.remove(); return; } const commaizedViewCount = viewCountNumber.toLocaleString(); const viewCountBody = document.getElementById('work-metadata-view-count'); if (!viewCountBody) { throw new Error('Failed to find work views element'); } viewCountBody.textContent = `${commaizedViewCount} views`; } catch (error) { // Remove the whole views element if there was some issue parsing. document.getElementById('work-metadata-view-count')?.parentNode?.remove(); throw new Error(`Failed to parse view count: ${viewCount}`, error); } }; // If the DOM is still loading, wait for it to be ready before updating the view count. if (document.readyState === "loading") { document.addEventListener('DOMContentLoaded', () => { updateViewCount(viewCount); }); // Otherwise, just update it immediately. } else { updateViewCount(viewCount); } })();</script></div><p class="ds-work-card--work-abstract ds-work-card--detail ds2-5-body-md">In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input and output warping, admits exact marginal log-likelihood optimisation and is robust to the values of learned parameters. We demonstrate HEBO’s empirical efficacy on the NeurIPS 2020 Black-Box Optimisation challenge, where HEBO placed first. Upon further analysis, we observe that HEBO significantly outperforms existing black-box optimisers on 108 machine learning hyperparameter tuning tasks comprising the Bayesmark benchmark. Our findings indicate that the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, multi-objective acquisition ensembles with Pareto...</p><div class="ds-work-card--button-container"><button class="ds2-5-button js-swp-download-button" data-signup-modal="{"location":"continue-reading-button--work-card","attachmentId":110554725,"attachmentType":"pdf","workUrl":"https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation"}">See full PDF</button><button class="ds2-5-button ds2-5-button--secondary js-swp-download-button" data-signup-modal="{"location":"download-pdf-button--work-card","attachmentId":110554725,"attachmentType":"pdf","workUrl":"https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation"}"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">download</span>Download PDF</button></div><div class="ds-signup-banner-trigger-container"><div class="ds-signup-banner-trigger ds-signup-banner-trigger-control"></div></div><div class="ds-signup-banner ds-signup-banner-control"><div id="ds-signup-banner-close-button"><button class="ds2-5-button ds2-5-button--secondary ds2-5-button--inverse"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">close</span></button></div><div class="ds-signup-banner-ctas" data-impression-entity-id="113649419" data-impression-entity-type="2" data-impression-source="signup-banner"><img src="//a.academia-assets.com/images/academia-logo-capital-white.svg" /><h4 class="ds2-5-heading-serif-sm">Sign up for access to the world's latest research</h4><button class="ds2-5-button ds2-5-button--inverse ds2-5-button--full-width js-swp-download-button" data-signup-modal="{"location":"signup-banner"}">Sign up for free<span class="material-symbols-outlined" style="font-size: 20px" translate="no">arrow_forward</span></button></div><div class="ds-signup-banner-divider"></div><div class="ds-signup-banner-reasons"><div class="ds-signup-banner-reasons-item"><span class="material-symbols-outlined" style="font-size: 24px" translate="no">check</span><span>Get notified about relevant papers</span></div><div class="ds-signup-banner-reasons-item"><span class="material-symbols-outlined" style="font-size: 24px" translate="no">check</span><span>Save papers to use in your research</span></div><div class="ds-signup-banner-reasons-item"><span class="material-symbols-outlined" style="font-size: 24px" translate="no">check</span><span>Join the discussion with peers</span></div><div class="ds-signup-banner-reasons-item"><span class="material-symbols-outlined" style="font-size: 24px" translate="no">check</span><span>Track your impact</span></div></div></div><script>(() => { // Set up signup banner show/hide behavior: // 1. If the signup banner trigger (a 242px-high* invisible div underneath the 'See Full PDF' / 'Download PDF' buttons) // is already fully scrolled above the viewport, show the banner by default // 2. If the signup banner trigger is fully visible, show the banner // 3. If the signup banner trigger has even a few pixels scrolled below the viewport, hide the banner // // * 242px is the empirically determined height of the signup banner. It's better to be a bit taller than // necessary than too short, so it's fine that the mobile (small breakpoint) banner is shorter. // First check session storage for the signup banner's visibility state const signupBannerHidden = sessionStorage.getItem('ds-signup-banner-hidden'); if (signupBannerHidden === 'true') { return; } const signupBanner = document.querySelector('.ds-signup-banner'); const signupBannerTrigger = document.querySelector('.ds-signup-banner-trigger'); if (!signupBannerTrigger) { window.Sentry.captureMessage("Signup banner trigger not found"); return; } let footerShown = false; window.addEventListener('load', () => { const rect = signupBannerTrigger.getBoundingClientRect(); // If page loaded up already scrolled below the trigger (via scroll restoration), show the banner by default if (rect.bottom < 0) { footerShown = true; signupBanner.classList.add('ds-signup-banner-visible'); } }); // Wait for trigger to fully enter viewport before showing banner (ensures PDF CTAs are never covered by banner) const observer = new IntersectionObserver((entries) => { entries.forEach(entry => { if (entry.isIntersecting && !footerShown) { footerShown = true; signupBanner.classList.add('ds-signup-banner-visible'); } else if (!entry.isIntersecting && footerShown) { if (signupBannerTrigger.getBoundingClientRect().bottom > 0) { footerShown = false; signupBanner.classList.remove('ds-signup-banner-visible'); } } }); }); observer.observe(signupBannerTrigger); // Set up signup banner close button event handler: const signupBannerCloseButton = document.querySelector('#ds-signup-banner-close-button'); signupBannerCloseButton.addEventListener('click', () => { signupBanner.classList.remove('ds-signup-banner-visible'); observer.unobserve(signupBannerTrigger); // Store the signup banner's visibility state in session storage sessionStorage.setItem('ds-signup-banner-hidden', 'true'); }); })();</script></div></div></div><div data-auto_select="false" data-client_id="331998490334-rsn3chp12mbkiqhl6e7lu2q0mlbu0f1b" data-doc_id="110554725" data-landing_url="https://www.academia.edu/113649419/An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation" data-login_uri="https://www.academia.edu/registrations/google_one_tap" data-moment_callback="onGoogleOneTapEvent" id="g_id_onload"></div><div class="ds-top-related-works--grid-container"><div class="ds-related-content--container ds-top-related-works--container"><h2 class="ds-related-content--heading">Related papers</h2><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="0" data-entity-id="113649420" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/113649420/HEBO_An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation">HEBO: An Empirical Study of Assumptions in Bayesian Optimisation</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="67755877" href="https://independent.academia.edu/alexandremaraval">alexandre maraval</a></div><p class="ds-related-work--metadata ds2-5-body-xs">Journal of Artificial Intelligence Research</p><p class="ds-related-work--abstract ds2-5-body-sm">In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input and output warping, admits exact marginal log-likelihood optimisation and is robust to the values of learned parameters. We demonstrate HEBO’s empirical efficacy on the NeurIPS 2020 Black-Box Optimisation challenge, where HEBO placed first. Upon further analysis, we observe that HEBO significantly outperforms existing black-box optimisers on 108 machine learning hyperparameter tuning tasks comprising the Bayesmark benchmark. Our findings indicate that the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, multiobjective acquisition ensembles with Pareto ...</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"HEBO: An Empirical Study of Assumptions in Bayesian Optimisation","attachmentId":110554727,"attachmentType":"pdf","work_url":"https://www.academia.edu/113649420/HEBO_An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/113649420/HEBO_An_Empirical_Study_of_Assumptions_in_Bayesian_Optimisation"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="1" data-entity-id="113649422" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/113649422/HEBO_Pushing_The_Limits_of_Sample_Efficient_Hyperparameter_Optimisation">HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="67755877" href="https://independent.academia.edu/alexandremaraval">alexandre maraval</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv (Cornell University), 2020</p><p class="ds-related-work--abstract ds2-5-body-sm">In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input and output warping, admits exact marginal log-likelihood optimisation and is robust to the values of learned parameters. We demonstrate HEBO's empirical efficacy on the NeurIPS 2020 Black-Box Optimisation challenge, where HEBO placed first. Upon further analysis, we observe that HEBO significantly outperforms existing black-box optimisers on 108 machine learning hyperparameter tuning tasks comprising the Bayesmark benchmark. Our findings indicate that the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, multi-objective acquisition ensembles with Pareto front solutions improve queried configurations, and robust acquisition maximisers afford empirical advantages relative to their non-robust counterparts. We hope these findings may serve as guiding principles for practitioners of Bayesian optimisation. All code is made available at https://github.com/huawei-noah/HEBO.</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation","attachmentId":110554729,"attachmentType":"pdf","work_url":"https://www.academia.edu/113649422/HEBO_Pushing_The_Limits_of_Sample_Efficient_Hyperparameter_Optimisation","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/113649422/HEBO_Pushing_The_Limits_of_Sample_Efficient_Hyperparameter_Optimisation"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="2" data-entity-id="127321557" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/127321557/Tuning_Hyperparameters_without_Grad_Students_Scalable_and_Robust_Bayesian_Optimisation_with_Dragonfly">Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="326958480" href="https://independent.academia.edu/biswajitParia3">biswajit Paria</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv (Cornell University), 2019</p><p class="ds-related-work--abstract ds2-5-body-sm">Bayesian Optimisation (BO) refers to a suite of techniques for global optimisation of expensive black box functions, which use introspective Bayesian models of the function to efficiently search for the optimum. While BO has been applied successfully in many applications, modern optimisation tasks usher in new challenges where conventional methods fail spectacularly. In this work, we present Dragonfly, an open source Python library for scalable and robust BO. Dragonfly incorporates multiple recently developed methods that allow BO to be applied in challenging real world settings; these include better methods for handling higher dimensional domains, methods for handling multi-fidelity evaluations when cheap approximations of an expensive function are available, methods for optimising over structured combinatorial spaces, such as the space of neural network architectures, and methods for handling parallel evaluations. Additionally, we develop new methodological improvements in BO for selecting the Bayesian model, selecting the acquisition function, and optimising over complex domains with different variable types and additional constraints. We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO. The Dragonfly library is available at dragonfly.github.io.</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly","attachmentId":121071092,"attachmentType":"pdf","work_url":"https://www.academia.edu/127321557/Tuning_Hyperparameters_without_Grad_Students_Scalable_and_Robust_Bayesian_Optimisation_with_Dragonfly","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/127321557/Tuning_Hyperparameters_without_Grad_Students_Scalable_and_Robust_Bayesian_Optimisation_with_Dragonfly"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="3" data-entity-id="96979950" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/96979950/Automatic_tuning_of_hyperparameters_using_Bayesian_optimization">Automatic tuning of hyperparameters using Bayesian optimization</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="215684484" href="https://independent.academia.edu/HelenVictoriaA">Helen Victoria A</a></div><p class="ds-related-work--metadata ds2-5-body-xs">Evolving Systems, 2020</p><p class="ds-related-work--abstract ds2-5-body-sm">Deep learning is a field in artificial intelligence that works well in computer vision, natural language processing and audio recognition. Deep neural network architectures has number of layers to conceive the features well, by itself. The hyperparameter tuning plays a major role in every dataset which has major effect in the performance of the training model. Due to the large dimensionality of data it is impossible to tune the parameters by human expertise. In this paper, we have used the CIFAR-10 Dataset and applied the Bayesian hyperparameter optimization algorithm to enhance the performance of the model. Bayesian optimization can be used for any noisy black box function for hyperparameter tuning. In this work Bayesian optimization clearly obtains optimized values for all hyperparameters which saves time and improves performance. The results also show that the error has been reduced in graphical processing unit than in CPU by 6.2% in the validation. Achieving global optimization in the trained model helps transfer learning across domains as well.</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Automatic tuning of hyperparameters using Bayesian optimization","attachmentId":98728286,"attachmentType":"pdf","work_url":"https://www.academia.edu/96979950/Automatic_tuning_of_hyperparameters_using_Bayesian_optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/96979950/Automatic_tuning_of_hyperparameters_using_Bayesian_optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="4" data-entity-id="63364895" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/63364895/Automatic_Setting_of_DNN_Hyper_Parameters_by_Mixing_Bayesian_Optimization_and_Tuning_Rules">Automatic Setting of DNN Hyper-Parameters by Mixing Bayesian Optimization and Tuning Rules</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="123812306" href="https://ferrara.academia.edu/michelefraccaroli">michele fraccaroli</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2020</p><p class="ds-related-work--abstract ds2-5-body-sm">Deep learning techniques play an increasingly important role in industrial and research environments due to their outstanding results. However, the large number of hyper-parameters to be set may lead to errors if they are set manually. The state-of-the-art hyper-parameters tuning methods are grid search, random search, and Bayesian Optimization. The first two methods are expensive because they try, respectively, all possible combinations and random combinations of hyper-parameters. Bayesian Optimization, instead, builds a surrogate model of the objective function, quantifies the uncertainty in the surrogate using Gaussian Process Regression and uses an acquisition function to decide where to sample the new set of hyper-parameters. This work faces the field of Hyper-Parameters Optimization (HPO). The aim is to improve Bayesian Optimization applied to Deep Neural Networks. For this goal, we build a new algorithm for evaluating and analyzing the results of the network on the training a...</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Automatic Setting of DNN Hyper-Parameters by Mixing Bayesian Optimization and Tuning Rules","attachmentId":75818315,"attachmentType":"pdf","work_url":"https://www.academia.edu/63364895/Automatic_Setting_of_DNN_Hyper_Parameters_by_Mixing_Bayesian_Optimization_and_Tuning_Rules","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/63364895/Automatic_Setting_of_DNN_Hyper_Parameters_by_Mixing_Bayesian_Optimization_and_Tuning_Rules"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="5" data-entity-id="80628542" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/80628542/Calibration_Improves_Bayesian_Optimization">Calibration Improves Bayesian Optimization</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="43309376" href="https://iitb.academia.edu/ShachiDeshpande">Shachi Deshpande</a></div><p class="ds-related-work--metadata ds2-5-body-xs">ArXiv, 2021</p><p class="ds-related-work--abstract ds2-5-body-sm">Bayesian optimization is a procedure that allows obtaining the global optimum of black-box functions and that is useful in applications such as hyper-parameter optimization. Uncertainty estimates over the shape of the objective function are instrumental in guiding the optimization process. However, these estimates can be inaccurate if the objective function violates assumptions made within the underlying model (e.g., Gaussianity). We propose a simple algorithm to calibrate the uncertainty of posterior distributions over the objective function as part of the Bayesian optimization process. We show that by improving the uncertainty estimates of the posterior distribution with calibration, Bayesian optimization makes better decisions and arrives at the global optimum in fewer steps. We show that this technique improves the performance of Bayesian optimization on standard benchmark functions and hyperparameter optimization tasks.</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Calibration Improves Bayesian Optimization","attachmentId":86947417,"attachmentType":"pdf","work_url":"https://www.academia.edu/80628542/Calibration_Improves_Bayesian_Optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/80628542/Calibration_Improves_Bayesian_Optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="6" data-entity-id="26986691" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/26986691/Practical_Bayesian_Optimization_of_Machine_Learning_Algorithms">Practical Bayesian Optimization of Machine Learning Algorithms</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="51009810" href="https://independent.academia.edu/lethanhPhong2">le thanh Phong</a></div><p class="ds-related-work--abstract ds2-5-body-sm">The use of machine learning algorithms frequently involves careful tuning of learning parameters and model hyperparameters. Unfortunately, this tuning is often a " black art " requiring expert experience, rules of thumb, or sometimes brute-force search. There is therefore great appeal for automatic approaches that can optimize the performance of any given learning algorithm to the problem at hand. In this work, we consider this problem through the framework of Bayesian optimization , in which a learning algorithm's generalization performance is modeled as a sample from a Gaussian process (GP). We show that certain choices for the nature of the GP, such as the type of kernel and the treatment of its hyperparame-ters, can play a crucial role in obtaining a good optimizer that can achieve expert-level performance. We describe new algorithms that take into account the variable cost (duration) of learning algorithm experiments and that can leverage the presence of multiple cores for parallel experimentation. We show that these proposed algorithms improve on previous automatic procedures and can reach or surpass human expert-level optimization for many algorithms including latent Dirichlet allocation, structured SVMs and convolutional neural networks.</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Practical Bayesian Optimization of Machine Learning Algorithms","attachmentId":47247998,"attachmentType":"pdf","work_url":"https://www.academia.edu/26986691/Practical_Bayesian_Optimization_of_Machine_Learning_Algorithms","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/26986691/Practical_Bayesian_Optimization_of_Machine_Learning_Algorithms"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="7" data-entity-id="71104432" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/71104432/Pareto_efficient_Acquisition_Functions_for_Cost_Aware_Bayesian_Optimization">Pareto-efficient Acquisition Functions for Cost-Aware Bayesian Optimization</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="160417551" href="https://mit.academia.edu/gauthierguinet">gauthier guinet</a></div><p class="ds-related-work--metadata ds2-5-body-xs">ArXiv, 2020</p><p class="ds-related-work--abstract ds2-5-body-sm">Bayesian optimization (BO) is a popular method to optimize expensive black-box functions. It efficiently tunes machine learning algorithms under the implicit assumption that hyperparameter evaluations cost approximately the same. In reality, the cost of evaluating different hyperparameters, be it in terms of time, dollars or energy, can span several orders of magnitude of difference. While a number of heuristics have been proposed to make BO cost-aware, none of these have been proven to work robustly. In this work, we reformulate cost-aware BO in terms of Pareto efficiency and introduce the cost Pareto Front, a mathematical object allowing us to highlight the shortcomings of commonly used acquisition functions. Based on this, we propose a novel Pareto-efficient adaptation of the expected improvement. On 144 real-world black-box function optimization problems we show that our Pareto-efficient acquisition functions significantly outperform previous solutions, bringing up to 50% speed-...</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Pareto-efficient Acquisition Functions for Cost-Aware Bayesian Optimization","attachmentId":80597191,"attachmentType":"pdf","work_url":"https://www.academia.edu/71104432/Pareto_efficient_Acquisition_Functions_for_Cost_Aware_Bayesian_Optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/71104432/Pareto_efficient_Acquisition_Functions_for_Cost_Aware_Bayesian_Optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="8" data-entity-id="90032062" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/90032062/Lifelong_Bayesian_Optimization">Lifelong Bayesian Optimization</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="243800885" href="https://independent.academia.edu/ahmedalaa472">ahmed alaa</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2019</p><p class="ds-related-work--abstract ds2-5-body-sm">Automatic Machine Learning (Auto-ML) systems tackle the problem of automating the design of prediction models or pipelines for data science. In this paper, we present Lifelong Bayesian Optimization (LBO), an online, multitask Bayesian optimization (BO) algorithm designed to solve the problem of model selection for datasets arriving and evolving over time. To be suitable for "lifelong" Bayesian optimization, an algorithm needs to scale with the ever increasing number of acquisitions and should be able to leverage past optimizations in learning the current best model. In LBO, we exploit the correlation between black-box functions by using components of previously learned functions to speed up the learning process for newly arriving datasets. Experiments on real and synthetic data show that LBO outperforms standard BO algorithms applied repeatedly on the data. Preprint. Under review.</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Lifelong Bayesian Optimization","attachmentId":93707918,"attachmentType":"pdf","work_url":"https://www.academia.edu/90032062/Lifelong_Bayesian_Optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/90032062/Lifelong_Bayesian_Optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-wsj-grid-card" data-collection-position="9" data-entity-id="108991398" data-sort-order="default"><a class="ds-related-work--title js-wsj-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/108991398/Bayesian_Optimization_for_Selecting_Efficient_Machine_Learning_Models">Bayesian Optimization for Selecting Efficient Machine Learning Models</a><div class="ds-related-work--metadata"><a class="js-wsj-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="31060757" href="https://independent.academia.edu/TrungHBui">Trung H. Bui</a></div><p class="ds-related-work--metadata ds2-5-body-xs">ArXiv, 2020</p><p class="ds-related-work--abstract ds2-5-body-sm">The performance of many machine learning models depends on their hyper-parameter settings. Bayesian Optimization has become a successful tool for hyper-parameter optimization of machine learning algorithms, which aims to identify optimal hyper-parameters during an iterative sequential process. However, most of the Bayesian Optimization algorithms are designed to select models for effectiveness only and ignore the important issue of model training efficiency. Given that both model effectiveness and training time are important for real-world applications, models selected for effectiveness may not meet the strict training time requirements necessary to deploy in a production environment. In this work, we present a unified Bayesian Optimization framework for jointly optimizing models for both prediction effectiveness and training efficiency. We propose an objective that captures the tradeoff between these two metrics and demonstrate how we can jointly optimize them in a principled Bayes...</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Bayesian Optimization for Selecting Efficient Machine Learning Models","attachmentId":107239828,"attachmentType":"pdf","work_url":"https://www.academia.edu/108991398/Bayesian_Optimization_for_Selecting_Efficient_Machine_Learning_Models","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-wsj-grid-card-view-pdf" href="https://www.academia.edu/108991398/Bayesian_Optimization_for_Selecting_Efficient_Machine_Learning_Models"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div></div></div><div class="ds-sticky-ctas--wrapper js-loswp-sticky-ctas hidden"><div class="ds-sticky-ctas--grid-container"><div class="ds-sticky-ctas--container"><button class="ds2-5-button js-swp-download-button" data-signup-modal="{"location":"continue-reading-button--sticky-ctas","attachmentId":110554725,"attachmentType":"pdf","workUrl":null}">See full PDF</button><button class="ds2-5-button ds2-5-button--secondary js-swp-download-button" data-signup-modal="{"location":"download-pdf-button--sticky-ctas","attachmentId":110554725,"attachmentType":"pdf","workUrl":null}"><span class="material-symbols-outlined" style="font-size: 20px" translate="no">download</span>Download PDF</button></div></div></div><div class="ds-below-fold--grid-container"><div class="ds-work--container js-loswp-embedded-document"><div class="attachment_preview" data-attachment="Attachment_110554725" style="display: none"><div class="js-scribd-document-container"><div class="scribd--document-loading js-scribd-document-loader" style="display: block;"><img alt="Loading..." src="//a.academia-assets.com/images/loaders/paper-load.gif" /><p>Loading Preview</p></div></div><div style="text-align: center;"><div class="scribd--no-preview-alert js-preview-unavailable"><p>Sorry, preview is currently unavailable. You can download the paper by clicking the button above.</p></div></div></div></div><div class="ds-sidebar--container js-work-sidebar"><div class="ds-related-content--container"><h2 class="ds-related-content--heading">Related papers</h2><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="0" data-entity-id="81408586" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/81408586/Sherpa_Hyperparameter_Optimization_for_Machine_Learning_Models">Sherpa: Hyperparameter Optimization for Machine Learning Models</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="39569978" href="https://uci.academia.edu/PeterSadowski">Peter Sadowski</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2018</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Sherpa: Hyperparameter Optimization for Machine Learning Models","attachmentId":87461221,"attachmentType":"pdf","work_url":"https://www.academia.edu/81408586/Sherpa_Hyperparameter_Optimization_for_Machine_Learning_Models","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/81408586/Sherpa_Hyperparameter_Optimization_for_Machine_Learning_Models"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="1" data-entity-id="72142091" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/72142091/OptABC_an_Optimal_Hyperparameter_Tuning_Approach_for_Machine_Learning_Algorithms">OptABC: an Optimal Hyperparameter Tuning Approach for Machine Learning Algorithms</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="119898562" href="https://fiu.academia.edu/LeilaZahedi">Leila Zahedi</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"OptABC: an Optimal Hyperparameter Tuning Approach for Machine Learning Algorithms","attachmentId":81259761,"attachmentType":"pdf","work_url":"https://www.academia.edu/72142091/OptABC_an_Optimal_Hyperparameter_Tuning_Approach_for_Machine_Learning_Algorithms","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/72142091/OptABC_an_Optimal_Hyperparameter_Tuning_Approach_for_Machine_Learning_Algorithms"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="2" data-entity-id="102827351" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/102827351/Heteroscedastic_Treed_Bayesian_Optimisation">Heteroscedastic Treed Bayesian Optimisation</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="846270" href="https://oxford.academia.edu/YannisAssael">Yannis Assael</a></div><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Heteroscedastic Treed Bayesian Optimisation","attachmentId":102993500,"attachmentType":"pdf","work_url":"https://www.academia.edu/102827351/Heteroscedastic_Treed_Bayesian_Optimisation","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/102827351/Heteroscedastic_Treed_Bayesian_Optimisation"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="3" data-entity-id="96276925" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/96276925/Machine_Learning_Model_Optimization_with_Hyper_Parameter_Tuning_Approach">Machine Learning Model Optimization with Hyper Parameter Tuning Approach</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="248576768" href="https://independent.academia.edu/RiyadHossain74">Riyad Hossain</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2021</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Machine Learning Model Optimization with Hyper Parameter Tuning Approach","attachmentId":98220794,"attachmentType":"pdf","work_url":"https://www.academia.edu/96276925/Machine_Learning_Model_Optimization_with_Hyper_Parameter_Tuning_Approach","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/96276925/Machine_Learning_Model_Optimization_with_Hyper_Parameter_Tuning_Approach"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="4" data-entity-id="121431118" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/121431118/Multi_objective_hyperparameter_tuning_via_random_search_on_deep_learning_models">Multi objective hyperparameter tuning via random search on deep learning models</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="163561779" href="https://uad.academia.edu/TELKOMNIKAJOURNAL">TELKOMNIKA JOURNAL</a></div><p class="ds-related-work--metadata ds2-5-body-xs">TELKOMNIKA Telecommunication Computing Electronics and Control, 2024</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Multi objective hyperparameter tuning via random search on deep learning models","attachmentId":116308033,"attachmentType":"pdf","work_url":"https://www.academia.edu/121431118/Multi_objective_hyperparameter_tuning_via_random_search_on_deep_learning_models","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/121431118/Multi_objective_hyperparameter_tuning_via_random_search_on_deep_learning_models"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="5" data-entity-id="79040450" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/79040450/Solving_Black_Box_Optimization_Challenge_via_Learning_Search_Space_Partition_for_Local_Bayesian_Optimization">Solving Black-Box Optimization Challenge via Learning Search Space Partition for Local Bayesian Optimization</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="121180616" href="https://independent.academia.edu/YazidKadir">Yazid Kadir</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2020</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Solving Black-Box Optimization Challenge via Learning Search Space Partition for Local Bayesian Optimization","attachmentId":85894678,"attachmentType":"pdf","work_url":"https://www.academia.edu/79040450/Solving_Black_Box_Optimization_Challenge_via_Learning_Search_Space_Partition_for_Local_Bayesian_Optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/79040450/Solving_Black_Box_Optimization_Challenge_via_Learning_Search_Space_Partition_for_Local_Bayesian_Optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="6" data-entity-id="89020172" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/89020172/Hybrid_Batch_Bayesian_Optimization">Hybrid Batch Bayesian Optimization</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="225755520" href="https://independent.academia.edu/javadazimi6">javad azimi</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2012</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Hybrid Batch Bayesian Optimization","attachmentId":92894781,"attachmentType":"pdf","work_url":"https://www.academia.edu/89020172/Hybrid_Batch_Bayesian_Optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/89020172/Hybrid_Batch_Bayesian_Optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="7" data-entity-id="125315074" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/125315074/Batch_Multi_Fidelity_Bayesian_Optimization_with_Deep_Auto_Regressive_Networks">Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="318927884" href="https://independent.academia.edu/ShandianZhe">Shandian Zhe</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv (Cornell University), 2021</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks","attachmentId":119381542,"attachmentType":"pdf","work_url":"https://www.academia.edu/125315074/Batch_Multi_Fidelity_Bayesian_Optimization_with_Deep_Auto_Regressive_Networks","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/125315074/Batch_Multi_Fidelity_Bayesian_Optimization_with_Deep_Auto_Regressive_Networks"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="8" data-entity-id="58209158" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/58209158/Weighted_Random_Search_for_Hyperparameter_Optimization">Weighted Random Search for Hyperparameter Optimization</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="997893" href="https://cwu.academia.edu/RazvanAndonie">Razvan Andonie</a></div><p class="ds-related-work--metadata ds2-5-body-xs">International Journal of Computers Communications & Control</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Weighted Random Search for Hyperparameter Optimization","attachmentId":72730944,"attachmentType":"pdf","work_url":"https://www.academia.edu/58209158/Weighted_Random_Search_for_Hyperparameter_Optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/58209158/Weighted_Random_Search_for_Hyperparameter_Optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="9" data-entity-id="81408582" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/81408582/Sherpa_Robust_hyperparameter_optimization_for_machine_learning">Sherpa: Robust hyperparameter optimization for machine learning</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="39569978" href="https://uci.academia.edu/PeterSadowski">Peter Sadowski</a></div><p class="ds-related-work--metadata ds2-5-body-xs">SoftwareX, 2020</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Sherpa: Robust hyperparameter optimization for machine learning","attachmentId":87461264,"attachmentType":"pdf","work_url":"https://www.academia.edu/81408582/Sherpa_Robust_hyperparameter_optimization_for_machine_learning","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/81408582/Sherpa_Robust_hyperparameter_optimization_for_machine_learning"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="10" data-entity-id="77218720" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/77218720/Hyperopt_A_Python_Library_for_Optimizing_the_Hyperparameters_of_Machine_Learning_Algorithms">Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="2635076" href="https://mit.academia.edu/DanielYamins">Daniel Yamins</a></div><p class="ds-related-work--metadata ds2-5-body-xs">Proceedings of the 12th Python in Science Conference, 2013</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms","attachmentId":84655280,"attachmentType":"pdf","work_url":"https://www.academia.edu/77218720/Hyperopt_A_Python_Library_for_Optimizing_the_Hyperparameters_of_Machine_Learning_Algorithms","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/77218720/Hyperopt_A_Python_Library_for_Optimizing_the_Hyperparameters_of_Machine_Learning_Algorithms"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="11" data-entity-id="99411084" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/99411084/A_System_for_Massively_Parallel_Hyperparameter_Tuning">A System for Massively Parallel Hyperparameter Tuning</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="264023175" href="https://independent.academia.edu/LiamLi23">Liam Li</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv: Learning, 2020</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"A System for Massively Parallel Hyperparameter Tuning","attachmentId":100508366,"attachmentType":"pdf","work_url":"https://www.academia.edu/99411084/A_System_for_Massively_Parallel_Hyperparameter_Tuning","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/99411084/A_System_for_Massively_Parallel_Hyperparameter_Tuning"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="12" data-entity-id="126867568" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/126867568/Asynchronous_epsilon_Greedy_Bayesian_Optimisation">Asynchronous \epsilon-Greedy Bayesian Optimisation</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="31636764" href="https://independent.academia.edu/EversonR">Richard Everson</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv (Cornell University), 2020</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Asynchronous \\epsilon-Greedy Bayesian Optimisation","attachmentId":120682607,"attachmentType":"pdf","work_url":"https://www.academia.edu/126867568/Asynchronous_epsilon_Greedy_Bayesian_Optimisation","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/126867568/Asynchronous_epsilon_Greedy_Bayesian_Optimisation"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="13" data-entity-id="99411080" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/99411080/Massively_Parallel_Hyperparameter_Tuning">Massively Parallel Hyperparameter Tuning</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="264023175" href="https://independent.academia.edu/LiamLi23">Liam Li</a></div><p class="ds-related-work--metadata ds2-5-body-xs">ArXiv, 2018</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Massively Parallel Hyperparameter Tuning","attachmentId":100508322,"attachmentType":"pdf","work_url":"https://www.academia.edu/99411080/Massively_Parallel_Hyperparameter_Tuning","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/99411080/Massively_Parallel_Hyperparameter_Tuning"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="14" data-entity-id="98897367" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/98897367/Scalable_Bayesian_optimization_with_high_dimensional_outputs_using_randomized_prior_networks">Scalable Bayesian optimization with high-dimensional outputs using randomized prior networks</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="39863824" href="https://mit.academia.edu/MohamedAzizBhouri">Mohamed Aziz Bhouri</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv (Cornell University), 2023</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Scalable Bayesian optimization with high-dimensional outputs using randomized prior networks","attachmentId":100144077,"attachmentType":"pdf","work_url":"https://www.academia.edu/98897367/Scalable_Bayesian_optimization_with_high_dimensional_outputs_using_randomized_prior_networks","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/98897367/Scalable_Bayesian_optimization_with_high_dimensional_outputs_using_randomized_prior_networks"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="15" data-entity-id="125315062" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/125315062/Multi_Fidelity_Bayesian_Optimization_via_Deep_Neural_Networks">Multi-Fidelity Bayesian Optimization via Deep Neural Networks</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="318927884" href="https://independent.academia.edu/ShandianZhe">Shandian Zhe</a></div><p class="ds-related-work--metadata ds2-5-body-xs">ArXiv, 2020</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Multi-Fidelity Bayesian Optimization via Deep Neural Networks","attachmentId":119381554,"attachmentType":"pdf","work_url":"https://www.academia.edu/125315062/Multi_Fidelity_Bayesian_Optimization_via_Deep_Neural_Networks","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/125315062/Multi_Fidelity_Bayesian_Optimization_via_Deep_Neural_Networks"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="16" data-entity-id="73002531" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/73002531/%CE%B5_shotgun_%CE%B5_greedy_Batch_Bayesian_Optimisation">ϵ-shotgun: ϵ-greedy Batch Bayesian Optimisation</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="31636764" href="https://independent.academia.edu/EversonR">Richard Everson</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2020</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"ϵ-shotgun: ϵ-greedy Batch Bayesian Optimisation","attachmentId":81698306,"attachmentType":"pdf","work_url":"https://www.academia.edu/73002531/%CE%B5_shotgun_%CE%B5_greedy_Batch_Bayesian_Optimisation","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/73002531/%CE%B5_shotgun_%CE%B5_greedy_Batch_Bayesian_Optimisation"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="17" data-entity-id="63656417" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/63656417/HYPPO_A_Surrogate_Based_Multi_Level_Parallelism_Tool_for_Hyperparameter_Optimization">HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="190525748" href="https://independent.academia.edu/CaseyGarner5">Casey Garner</a></div><p class="ds-related-work--metadata ds2-5-body-xs">ArXiv, 2021</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization","attachmentId":76013597,"attachmentType":"pdf","work_url":"https://www.academia.edu/63656417/HYPPO_A_Surrogate_Based_Multi_Level_Parallelism_Tool_for_Hyperparameter_Optimization","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/63656417/HYPPO_A_Surrogate_Based_Multi_Level_Parallelism_Tool_for_Hyperparameter_Optimization"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="18" data-entity-id="84909584" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/84909584/Hot_Swapping_for_Online_Adaptation_of_Optimization_Hyperparameters">Hot Swapping for Online Adaptation of Optimization Hyperparameters</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="46720553" href="https://independent.academia.edu/DennisDeCoste">Dennis DeCoste</a></div><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Hot Swapping for Online Adaptation of Optimization Hyperparameters","attachmentId":89774935,"attachmentType":"pdf","work_url":"https://www.academia.edu/84909584/Hot_Swapping_for_Online_Adaptation_of_Optimization_Hyperparameters","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/84909584/Hot_Swapping_for_Online_Adaptation_of_Optimization_Hyperparameters"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="19" data-entity-id="105943621" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/105943621/Alleviating_Search_Bias_in_Bayesian_Evolutionary_Optimization_with_Many_Heterogeneous_Objectives">Alleviating Search Bias in Bayesian Evolutionary Optimization with Many Heterogeneous Objectives</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="496137" href="https://independent.academia.edu/MarkusOlhofer">Markus Olhofer</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv (Cornell University), 2022</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Alleviating Search Bias in Bayesian Evolutionary Optimization with Many Heterogeneous Objectives","attachmentId":105272514,"attachmentType":"pdf","work_url":"https://www.academia.edu/105943621/Alleviating_Search_Bias_in_Bayesian_Evolutionary_Optimization_with_Many_Heterogeneous_Objectives","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/105943621/Alleviating_Search_Bias_in_Bayesian_Evolutionary_Optimization_with_Many_Heterogeneous_Objectives"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="20" data-entity-id="126867567" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/126867567/Asynchronous_%C3%8E%CE%BC_Greedy_Bayesian_Optimisation">Asynchronous Îµ-Greedy Bayesian Optimisation</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="31636764" href="https://independent.academia.edu/EversonR">Richard Everson</a></div><p class="ds-related-work--metadata ds2-5-body-xs">arXiv (Cornell University), 2021</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Asynchronous Îµ-Greedy Bayesian Optimisation","attachmentId":120682603,"attachmentType":"pdf","work_url":"https://www.academia.edu/126867567/Asynchronous_%C3%8E%CE%BC_Greedy_Bayesian_Optimisation","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/126867567/Asynchronous_%C3%8E%CE%BC_Greedy_Bayesian_Optimisation"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="21" data-entity-id="98770564" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/98770564/Black_Box_Optimization_Revisited_Improving_Algorithm_Selection_Wizards_Through_Massive_Benchmarking">Black-Box Optimization Revisited: Improving Algorithm Selection Wizards Through Massive Benchmarking</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="161099458" href="https://independent.academia.edu/PacoWong4">Paco Wong</a></div><p class="ds-related-work--metadata ds2-5-body-xs">IEEE Transactions on Evolutionary Computation, 2021</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Black-Box Optimization Revisited: Improving Algorithm Selection Wizards Through Massive Benchmarking","attachmentId":100031719,"attachmentType":"pdf","work_url":"https://www.academia.edu/98770564/Black_Box_Optimization_Revisited_Improving_Algorithm_Selection_Wizards_Through_Massive_Benchmarking","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/98770564/Black_Box_Optimization_Revisited_Improving_Algorithm_Selection_Wizards_Through_Massive_Benchmarking"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="22" data-entity-id="108143845" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/108143845/Filtering_Bayesian_optimization_approach_in_weakly_specified_search_space">Filtering Bayesian optimization approach in weakly specified search space</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="214605324" href="https://independent.academia.edu/V%C5%A9Ho%C3%A0ngNguy%E1%BB%85n2">Vũ Hoàng Nguyễn</a></div><p class="ds-related-work--metadata ds2-5-body-xs">Knowledge and Information Systems, 2018</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Filtering Bayesian optimization approach in weakly specified search space","attachmentId":106605930,"attachmentType":"pdf","work_url":"https://www.academia.edu/108143845/Filtering_Bayesian_optimization_approach_in_weakly_specified_search_space","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/108143845/Filtering_Bayesian_optimization_approach_in_weakly_specified_search_space"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div><div class="ds-related-work--container js-related-work-sidebar-card" data-collection-position="23" data-entity-id="103156644" data-sort-order="default"><a class="ds-related-work--title js-related-work-grid-card-title ds2-5-body-md ds2-5-body-link" href="https://www.academia.edu/103156644/Asynchronous_Batch_Bayesian_Optimisation_with_Improved_Local_Penalisation">Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation</a><div class="ds-related-work--metadata"><a class="js-related-work-grid-card-author ds2-5-body-sm ds2-5-body-link" data-author-id="273219242" href="https://independent.academia.edu/AhsanAlvi6">Ahsan Alvi</a></div><p class="ds-related-work--metadata ds2-5-body-xs">2019</p><div class="ds-related-work--ctas"><button class="ds2-5-text-link ds2-5-text-link--inline js-swp-download-button" data-signup-modal="{"location":"wsj-grid-card-download-pdf-modal","work_title":"Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation","attachmentId":103238210,"attachmentType":"pdf","work_url":"https://www.academia.edu/103156644/Asynchronous_Batch_Bayesian_Optimisation_with_Improved_Local_Penalisation","alternativeTracking":true}"><span class="material-symbols-outlined" style="font-size: 18px" translate="no">download</span><span class="ds2-5-text-link__content">Download free PDF</span></button><a class="ds2-5-text-link ds2-5-text-link--inline js-related-work-grid-card-view-pdf" href="https://www.academia.edu/103156644/Asynchronous_Batch_Bayesian_Optimisation_with_Improved_Local_Penalisation"><span class="ds2-5-text-link__content">View PDF</span><span class="material-symbols-outlined" style="font-size: 18px" translate="no">chevron_right</span></a></div></div></div><div class="ds-related-content--container"><h2 class="ds-related-content--heading">Related topics</h2><div class="ds-research-interests--pills-container"><a class="js-related-research-interest ds-research-interests--pill" data-entity-id="300" rel="nofollow" href="https://www.academia.edu/Documents/in/Mathematics">Mathematics</a><a class="js-related-research-interest ds-research-interests--pill" data-entity-id="422" rel="nofollow" href="https://www.academia.edu/Documents/in/Computer_Science">Computer Science</a><a class="js-related-research-interest ds-research-interests--pill" data-entity-id="2008" rel="nofollow" href="https://www.academia.edu/Documents/in/Machine_Learning">Machine Learning</a><a class="js-related-research-interest ds-research-interests--pill" data-entity-id="245189" rel="nofollow" href="https://www.academia.edu/Documents/in/Heteroscedasticity">Heteroscedasticity</a><a class="js-related-research-interest ds-research-interests--pill" data-entity-id="535039" rel="nofollow" href="https://www.academia.edu/Documents/in/Bayesian_Optimization">Bayesian Optimization</a><a class="js-related-research-interest ds-research-interests--pill" data-entity-id="1032783" rel="nofollow" href="https://www.academia.edu/Documents/in/Bayesian_Probability">Bayesian Probability</a></div></div></div></div></div><div class="footer--content"><ul class="footer--main-links hide-on-mobile"><li><a href="https://www.academia.edu/about">About</a></li><li><a href="https://www.academia.edu/press">Press</a></li><li><a href="https://www.academia.edu/documents">Papers</a></li><li><a href="https://www.academia.edu/topics">Topics</a></li><li><a href="https://www.academia.edu/hiring"><svg style="width: 13px; height: 13px; position: relative; bottom: -1px;" aria-hidden="true" focusable="false" data-prefix="fas" data-icon="briefcase" class="svg-inline--fa fa-briefcase fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M320 336c0 8.84-7.16 16-16 16h-96c-8.84 0-16-7.16-16-16v-48H0v144c0 25.6 22.4 48 48 48h416c25.6 0 48-22.4 48-48V288H320v48zm144-208h-80V80c0-25.6-22.4-48-48-48H176c-25.6 0-48 22.4-48 48v48H48c-25.6 0-48 22.4-48 48v80h512v-80c0-25.6-22.4-48-48-48zm-144 0H192V96h128v32z"></path></svg> <strong>We're Hiring!</strong></a></li><li><a href="https://support.academia.edu/hc/en-us"><svg style="width: 12px; height: 12px; position: relative; bottom: -1px;" aria-hidden="true" focusable="false" data-prefix="fas" data-icon="question-circle" class="svg-inline--fa fa-question-circle fa-w-16" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path fill="currentColor" d="M504 256c0 136.997-111.043 248-248 248S8 392.997 8 256C8 119.083 119.043 8 256 8s248 111.083 248 248zM262.655 90c-54.497 0-89.255 22.957-116.549 63.758-3.536 5.286-2.353 12.415 2.715 16.258l34.699 26.31c5.205 3.947 12.621 3.008 16.665-2.122 17.864-22.658 30.113-35.797 57.303-35.797 20.429 0 45.698 13.148 45.698 32.958 0 14.976-12.363 22.667-32.534 33.976C247.128 238.528 216 254.941 216 296v4c0 6.627 5.373 12 12 12h56c6.627 0 12-5.373 12-12v-1.333c0-28.462 83.186-29.647 83.186-106.667 0-58.002-60.165-102-116.531-102zM256 338c-25.365 0-46 20.635-46 46 0 25.364 20.635 46 46 46s46-20.636 46-46c0-25.365-20.635-46-46-46z"></path></svg> <strong>Help Center</strong></a></li></ul><ul class="footer--research-interests"><li>Find new research papers in:</li><li><a href="https://www.academia.edu/Documents/in/Physics">Physics</a></li><li><a href="https://www.academia.edu/Documents/in/Chemistry">Chemistry</a></li><li><a href="https://www.academia.edu/Documents/in/Biology">Biology</a></li><li><a href="https://www.academia.edu/Documents/in/Health_Sciences">Health Sciences</a></li><li><a href="https://www.academia.edu/Documents/in/Ecology">Ecology</a></li><li><a href="https://www.academia.edu/Documents/in/Earth_Sciences">Earth Sciences</a></li><li><a href="https://www.academia.edu/Documents/in/Cognitive_Science">Cognitive Science</a></li><li><a href="https://www.academia.edu/Documents/in/Mathematics">Mathematics</a></li><li><a href="https://www.academia.edu/Documents/in/Computer_Science">Computer Science</a></li></ul><ul class="footer--legal-links hide-on-mobile"><li><a href="https://www.academia.edu/terms">Terms</a></li><li><a href="https://www.academia.edu/privacy">Privacy</a></li><li><a href="https://www.academia.edu/copyright">Copyright</a></li><li>Academia ©2025</li></ul></div> </body> </html>