CINXE.COM
About – gradient science
<!DOCTYPE html> <html> <head> <meta charset="utf-8"> <meta http-equiv="X-UA-Compatible" content="IE=edge"> <title>About – gradient science</title> <link rel="dns-prefetch" href="//maxcdn.bootstrapcdn.com"> <link rel="dns-prefetch" href="//cdnjs.cloudflare.com"> <meta name="viewport" content="width=device-width, initial-scale=1"> <meta name="description" content="Research highlights and perspectives on machine learning and optimization from MadryLab."> <meta name="robots" content="all"> <meta name="author" content="Madry Lab"> <link rel="canonical" href="https://gradientscience.org/about/"> <link rel="alternate" type="application/rss+xml" title="RSS Feed for gradient science" href="/feed.xml" /> <!-- Custom CSS --> <link rel="stylesheet" href="/css/pixyll.css?202409050530" type="text/css"> <!-- Fonts --> <link href='//fonts.googleapis.com/css?family=Merriweather:900,900italic,300,300italic' rel='stylesheet' type='text/css'> <link href='//fonts.googleapis.com/css?family=Lato:900,300' rel='stylesheet' type='text/css'> <link href="//maxcdn.bootstrapcdn.com/font-awesome/latest/css/font-awesome.min.css" rel="stylesheet"> <!-- MathJax --> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ tex2jax: { inlineMath: [['$','$'], ['\\(','\\)']], processEscapes: true } }); </script> <script type="text/javascript" async src="//cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"> </script> <!-- Verifications --> <!-- Open Graph --> <!-- From: https://github.com/mmistakes/hpstr-jekyll-theme/blob/master/_includes/head.html --> <meta property="og:locale" content="en_US"> <meta property="og:type" content="article"> <meta property="og:title" content="About"> <meta property="og:description" content="Research highlights and perspectives on machine learning and optimization from MadryLab."> <meta property="og:url" content="https://gradientscience.org/about/"> <meta property="og:site_name" content="gradient science"> <!-- Twitter Card --> <meta name="twitter:card" content="summary" /> <meta name="twitter:title" content="About" /> <meta name="twitter:description" content="Research highlights and perspectives on machine learning and optimization from MadryLab." /> <meta name="twitter:url" content="https://gradientscience.org/about/" /> <!-- Icons --> <link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="/favicon-16x16.png"> <link rel="mask-icon" href="/safari-pinned-tab.svg" color="#5bbad5"> <meta name="theme-color" content="#ffffff"> <script type="text/javascript"> (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','//www.google-analytics.com/analytics.js','ga'); ga('create', 'UA-121873647-1', 'auto'); ga('send', 'pageview'); </script> </head> <body class="site"> <div class="site-wrap"> <header class="site-header px2 px-responsive"> <div class="mt2 wrap"> <div class="measure"> <a href="/" class="site-title"> <img src="/images/logo-short-red.png" alt="" width="60" style="margin: 0px 20px 0px 0px"> </a> <a href="/" class="site-title" style="margin-top: 18px; color: #A31F34">gradient science</a> <nav class="site-nav"> <a href="/about/">About</a> <a href="/feed.xml">RSS feed</a> <a href="/contact/">Contact</a> </nav> <div class="clearfix"></div> </div> </div> </header> <div class="post p2 p-responsive wrap" role="main"> <div class="measure"> <div class="post"> <header class="post-header"> <h1 class="h2">About</h1> </header> <article class="post-content"> <p>This blog is a platform for presenting research highlights, perspectives on the field, and various other updates written by the members of <a href="http://madry-lab.ml">MadryLab</a>.</p> <p>Our main focus is on developing a view on the key phenomena in modern machine learning that combines both theoretical insights and empirical examinations. Topics that are particularly close to our hearts are understanding the optimization landscape of deep learning, and the view on machine learning through the lens of security and robustness.</p> </article> </div> </div> </div> </div> <footer class="center"> <div class="measure"> <small> Theme available on <a href="https://github.com/johnotander/pixyll">GitHub</a>. </small> <footer> <a href="http://accessibility.mit.edu">Accessibility</a> </footer> </div> </footer> </body> </html>