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:20260922T113316
DTSTART;TZID=America/Detroit:20261002T100000
DTEND;TZID=America/Detroit:20261002T110000
SUMMARY:Workshop / Seminar:Statistical Learning with Tensors: Compression\, Communication\, and Completion
DESCRIPTION:Many modern statistical and machine learning problems involve parameters that are intrinsically multiway\, including spatiotemporal arrays\, network data\, and weight tensors in large neural networks. Although such objects can always be vectorized\, doing so ignores multilinear structure and can lead to substantially different statistical and computational behavior. Weight tensors from large language models will serve as a motivating example\, illustrating how tensor methods can preserve structural information that is lost under naive vectorization. This talk develops a unified perspective on recent work in tensor-structured learning through three themes: compression\, communication\, and completion. Methodologically\, I will discuss low-rank tensor parameterizations\, rank selection through optimism-based risk analysis\, communication-efficient randomized tensor algorithms\, and structured sampling schemes for tensor completion. A recurring goal is to obtain nonasymptotic guarantees that connect tensor geometry\, statistical error\, computational cost\, and sample or communication complexity with formal guarantees.
UID:152636-21914324@events.umich.edu
URL:https://events.umich.edu/event/152636
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:AEM Featured,seminar,statistics
LOCATION:West Hall - 340
CONTACT:
END:VEVENT
END:VCALENDAR