BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20241016T120000
DTEND;TZID=America/New_York:20241016T131500
DTSTAMP:20260603T050145
CREATED:20240715T210338Z
LAST-MODIFIED:20240715T210338Z
UID:11731-1729080000-1729084500@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: "Some Displaced Vignettes on Generalized Notions of Equivariance"
DESCRIPTION:Abstract: \nThe explicit incorporation of task-specific inductive biases through symmetry has emerged as a crucial design precept in the development of high-performance machine learning models. Symmetry-aware neural networks\, such as group equivariant networks\, have achieved notable success in areas like protein and drug design\, where capturing task-specific symmetries improves generalization. Recent efforts have focused on models that relax equivariance\, balancing flexibility and equivariance to enhance performance. In the first part of the talk\, I will discuss the benefits of partial and approximate equivariance from a theoretical perspective\, presenting quantitative bounds that demonstrate how models capturing task-specific symmetries lead to improved generalization. Utilizing this quantification\, I will examine the more general question of dealing with approximate/partial symmetries and model mis-spefication\, delineating conditions under which the model equivariance is optimal for a given level of data symmetry. In the second part\, I will present a general formalism based on special structured matrices\, which generalizes classical low-displacement rank theory of Kailath and co-workers\, which can help in constructing approximately equivariant neural networks with significantly reduced parameter counts. In the last part\, I will discuss some attempts at generalizing notions of equivariance in the context of language and compositional generalization. I will also talk about some ongoing work on using such notions for the problem of inverse protein folding. \nWork done in collaboration with: Mircea Petrace (Pontificia Universidad Católica de Chile)\, Ashwin Samudre (Simon Fraser University)\, Brian D. Nord (Fermilab and University of Chicago)\, and Payel Das (IBM Research). \nZoom Link (if unable to attend in-person): https://upenn.zoom.us/j/96014696752
URL:https://seasevents.nmsdev7.com/event/asset-seminar-shubhendu-trivedi-massachusetts-institute-of-technology/
LOCATION:Raisler Lounge (Room 225)\, Towne Building\, 220 South 33rd Street\, Philadelphia\, PA\, 19104\, United States
END:VEVENT
END:VCALENDAR