BEGIN:VCALENDAR VERSION:2.0 X-WR-CALNAME:EventsCalendar PRODID:-//hacksw/handcal//NONSGML v1.0//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York LAST-MODIFIED:20240422T053451Z TZURL:https://www.tzurl.org/zoneinfo-outlook/America/New_York X-LIC-LOCATION:America/New_York BEGIN:DAYLIGHT TZNAME:EDT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 DTSTART:19700308T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT BEGIN:STANDARD TZNAME:EST TZOFFSETFROM:-0400 TZOFFSETTO:-0500 DTSTART:19701101T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT CATEGORIES:Academic Affairs,Academic Resource Center,Alumni Event,College o f Arts and Sciences,College of Engineering,Graduate Studies,Lectures and S eminars DESCRIPTION:Joint Data and Computer Science Seminar Series Abstract: In thi s talk, we will explore the intersection between robust high-dimensional s tatistics and non-convex optimization. We will show that standard optimiza tion methods such as gradient descent can efficiently solve various robust estimation tasks, and conversely, robust estimation algorithms can be use d to develop robust algorithms for various tractable non-convex problems. Our results could lead to more practical and provably robust algorithms fo r many statistical and machine learning tasks, and shed light on the broad er connections between robust estimation and non-convex optimization. This talk is based on joint work with Ilias Diakonikolas, Jelena Diakonikolas, Haichen Dong, Rong Ge, Shivam Gupta, Daniel Kane, Shuyao Li, Alessio Mazz etto, Mahdi Soltanolkotabi, and Stephen Wright. Short Bio: Yu Cheng is an Assistant Professor in the Department of Computer Science at Brown Univers ity. He received his Ph.D. in Computer Science from the University of Sout hern California. Before joining Brown University, he was a postdoc at Duke University, a visiting member at the Institute for Advanced Study, and an Assistant Professor at the University of Illinois at Chicago. His main re search interests include machine learning, optimization, and game theory. Ìı Ìı Ìı Ìı\nEvent page: /events/cms/bridging-high-d imensional-robust-statistics-and-non-convex-optimization.php X-ALT-DESC;FMTTYPE=text/html:

ÌÇĞÄlogoÈë¿Ú

Joint Data and Computer Science Seminar Series

Abstract: In this talk\, we will explore the inter section between robust high-dimensional statistics and non-convex optimiza tion. We will show that standard optimization methods such as gradient des cent can efficiently solve various robust estimation tasks\, and conversel y\, robust estimation algorithms can be used to develop robust algorithms for various tractable non-convex problems. Our results could lead to more practical and provably robust algorithms for many statistical and machine learning tasks\, and shed light on the broader connections between robust estimation and non-convex optimization.

This talk is based on join t work with Ilias Diakonikolas\, Jelena Diakonikolas\, Haichen Dong\, Rong Ge\, Shivam Gupta\, Daniel Kane\, Shuyao Li\, Alessio Mazzetto\, Mahdi So ltanolkotabi\, and Stephen Wright.

Short Bio: Yu Cheng is an Assis tant Professor in the Department of Computer Science at Brown University. He received his Ph.D. in Computer Science from the University of Southern California. Before joining Brown University\, he was a postdoc at Duke Uni versity\, a visiting member at the Institute for Advanced Study\, and an A ssistant Professor at the University of Illinois at Chicago. His main rese arch interests include machine learning\, optimization\, and game theory.< /p>\n

Ìı

Event page: /events/cms/bridgi ng-high-dimensional-robust-statistics-and-non-convex-optimization.php< /a>

DTSTAMP:20260421T065824 DTSTART;TZID=America/New_York:20260422T133000 DTEND;TZID=America/New_York:20260422T143000 LOCATION:DION 311 SUMMARY;LANGUAGE=en-us:Bridging High-Dimensional Robust Statistics and Non- Convex Optimization UID:e439da179fa88cd30d3467302c0a6c98@www.umassd.edu END:VEVENT END:VCALENDAR