BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250204T133742
DTSTART;TZID=America/Detroit:20250207T100000
DTEND;TZID=America/Detroit:20250207T110000
SUMMARY:Workshop / Seminar:Statistics Department Seminar Series: Reese Pathak\, Ph.D. Candidate\, Department of Computer Science\, University of California\, Berkeley
DESCRIPTION:Abstract: Traditional machine learning often assumes that training (source) data closely resembles the testing (target) data. However\, in many contemporary applications this is unrealistic: in e-commerce\, consumer behavior is time-varying\; in medicine\, patient populations can exhibit more or less heterogeneity\; in autonomous driving\, models are rolled out to new environments. Ignoring these “distribution shifts” can lead to costly\, harmful\, and even dangerous outcomes. My research tackles these challenges by developing an algorithmic and statistical toolkit for addressing distribution shifts.\n\nThis talk focuses on covariate shift\, a form of distribution shift where the source and target distributions have different covariate laws. In the first part of the talk\, I demonstrate that for a large class of problems\, transfer learning is possible\, even when the source and target data have non-overlapping support. We introduce the “defect” of a covariate shift\, which quantifies the severity of a distribution shift. We demonstrate how the defect can be leveraged algorithmically\, leading to methods with optimal learning guarantees.\n\nIn the second part of the talk\, we refine the notion of defect to provide even stronger learning guarantees. We introduce a new method: penalized risk minimization with a non-traditional choice of regularization which is chosen via semidefinite programming. We show that our method has performance which is optimal with respect to the particular covariate shift instance. To our knowledge\, these are the first instance-optimal guarantees for transfer learning. Moreover\, our results are assumption-light: we impose essentially no restrictions on the underlying covariate laws\, thereby broadening the applicability of our theory.\n\nBased on the papers: https://doi.org/10.1214/23-AOS2268 and https://doi.org/10.1214/24-AOS2446\n\nhttps://people.eecs.berkeley.edu/~pathakr/
UID:130086-21865300@events.umich.edu
URL:https://events.umich.edu/event/130086
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:seminar
LOCATION:West Hall - 340
CONTACT:
END:VEVENT
END:VCALENDAR