{"id":171330,"date":"2014-04-04T06:19:02","date_gmt":"2014-04-04T06:19:02","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/project\/provable-non-convex-optimization-for-machine-learning-problems\/"},"modified":"2026-07-01T14:39:20","modified_gmt":"2026-07-01T21:39:20","slug":"provable-non-convex-optimization-for-machine-learning-problems","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/provable-non-convex-optimization-for-machine-learning-problems\/","title":{"rendered":"Provable Non-convex Optimization for Machine Learning Problems"},"content":{"rendered":"<p><em><strong>Note<\/strong>: This research project has reached its conclusion. These pages are maintained for reference and archival purposes.<\/em><\/p>\n<p>In this work, we explore theoretical properties of simple non-convex optimization methods for problems that feature prominently in several important areas such as recommendation systems, compressive sensing, computer vision etc.<\/p>\n<p><strong>Monographs<\/strong>:<\/p>\n<ul>\n<li>Non-convex Optimization for Machine Learning<br \/>\nFoundations and Trends in Machine Learning, <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"http:\/\/www.nowpublishers.com\/article\/Details\/MAL-058\">Official Site<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>, <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" rel=\"noopener noreferrer\" target=\"_blank\" href=\"https:\/\/arxiv.org\/abs\/1712.07897\">Arxiv<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/li>\n<\/ul>\n<p><strong>Talks<\/strong>:<\/p>\n<div id=\"en-usprojectsaltmindefault\" class=\"page-content\">\n<ul>\n<li>\n<div>Provable Non-convex Optimization for Machine Learning<br \/>\nSummer School on Non-convex Optimization, IIT Bombay, 2015 <a class=\"invalidLink\" href=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/\/altmin-day1.pptx\" target=\"_self\" rel=\"noopener noreferrer\">[part 1]<\/a> <a class=\"invalidLink\" href=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/\/altmin-day2.pptx\">[part 2]<\/a><\/div>\n<\/li>\n<li><a class=\"invalidLink\" href=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/\/altmin-ismp_iht.pdf\" target=\"_blank\" rel=\"noopener noreferrer\">Iterative Hard Thresholding for Sparse\/Low-rank Linear Regression<\/a> [PDF]<br \/>\nINRIA, France, 2015<\/li>\n<li>Iterative Hard\u00a0Thresholding for Robust Regression<br \/>\nITW, 2015<\/li>\n<li><a class=\"invalidLink\" href=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/altmin-altmin_pdf.pdf\" target=\"_blank\" rel=\"noopener noreferrer\">Provable Alternating Minimization Methods for Non-convex Optimization<\/a> [PDF]<br \/>\nIISC Bangalore, January 2014<\/li>\n<li>\n<div><a class=\"invalidLink\" href=\"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/altmin-altmin_web.pdf\" target=\"_blank\" rel=\"noopener noreferrer\">Provable Alternating Minimization methods for Low-rank Matrix Estimation Problems<\/a> [PDF]<br \/>\nICML, 2014<\/div>\n<\/li>\n<\/ul>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>We explore theoretical properties of simple non-convex optimization methods for problems that feature prominently in several important areas such as recommendation systems, compressive sensing, computer vision etc.<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13561,13556,13562],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-171330","msr-project","type-msr-project","status-publish","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-locale-en_us","msr-archive-status-complete"],"msr_project_start":"2014-04-04","related-publications":[255606,621072,621066,621057,621045,393413,326486,292328,255669,255654,255639,255615,163096,255576,255567,255558,255522,168840,167776,167773,167770,167765,167763,167757],"related-downloads":[],"related-videos":[192635,192637,285920],"related-groups":[144938,144940],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"related-researchers":[],"msr_research_lab":[199562],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171330","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":14,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171330\/revisions"}],"predecessor-version":[{"id":1177474,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171330\/revisions\/1177474"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=171330"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=171330"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=171330"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=171330"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=171330"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}