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:Abstract: In this talk, we will explore the intersection betwee n robust high-dimensional statistics and non-convex optimization. We will show that standard optimization methods such as gradient descent can effic iently solve various robust estimation tasks, and conversely, robust estim ation algorithms can be used to develop robust algorithms for various trac table non-convex problems. Our results could lead to more practical and pr ovably robust algorithms for many statistical and machine learning tasks, and shed light on the broader connections between robust estimation and no n-convex optimization. This talk is based on joint work with Ilias Diakoni kolas, Jelena Diakonikolas, Haichen Dong, Rong Ge, Shivam Gupta, Daniel Ka ne, Shuyao Li, Alessio Mazzetto, Mahdi Soltanolkotabi, and Stephen Wright. Short Bio: Yu Cheng is an Assistant Professor in the Department of Comput er Science at Brown University. He received his Ph.D. in Computer Science from the University of Southern California. Before joining Brown Universit y, he was a postdoc at Duke University, a visiting member at the Institute for Advanced Study, and an Assistant Professor at the University of Illin ois at Chicago. His main research interests include machine learning, opti mization, and game theory. \nEvent page: https://www.umassd.edu /events/cms/bridging-high-dimensional-robust-statistics-and-non-convex-opt imization.php X-ALT-DESC;FMTTYPE=text/html:

Abstract: In this talk\, we wil l explore the intersection between robust high-dimensional statistics and non-convex optimization. We will show that standard optimization methods s uch as gradient descent can efficiently solve various robust estimation ta sks\, and conversely\, 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 stati stical and machine learning tasks\, and shed light on the broader connecti ons between robust estimation and non-convex optimization.

This ta lk is based on joint work with Ilias Diakonikolas\, Jelena Diakonikolas\, Haichen Dong\, Rong Ge\, Shivam Gupta\, Daniel Kane\, Shuyao Li\, Alessio Mazzetto\, Mahdi Soltanolkotabi\, and Stephen Wright.

Short Bio: Y u Cheng is an Assistant Professor in the Department of Computer Science at Brown University. He received his Ph.D. in Computer Science from the Univ ersity of Southern California. Before joining Brown University\, he was a postdoc at Duke University\, a visiting member at the Institute for Advanc ed Study\, and an Assistant Professor at the University of Illinois at Chi cago. His main research interests include machine learning\, optimization\ , and game theory.

Event page: https://www.umassd.ed u/events/cms/bridging-high-dimensional-robust-statistics-and-non-convex-op timization.php

DTSTAMP:20260410T201053 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:f2adaaff7db61483bbcaa54c5d3a09c3@www.umassd.edu END:VEVENT END:VCALENDAR