BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:35343864-6232-4339-a462-393237363762
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Stochastic Approximation Algorithms with Decision-Dependent Da
 ta: The Case of Performative Prediction - Hoi-To Wai\, Assistant Professor
 \, CUHK
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20261101T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20241103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20251102T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20240310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20250309T020000
RDATE:20260308T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:84b3c881-dce6-4bff-8a66-0a18498f6604
DTSTAMP:20260501T041859Z
CLASS:PUBLIC
CREATED:20241206T222743Z
DESCRIPTION:Abstract: Stochastic approximation (SA) forms the foundation of
  numerous online decision-making algorithms under uncertainty. In recent y
 ears\, it has garnered renewed interest in the dynamic environment setting
  where streaming data is not independent and identically distributed (i.i.
 d.)\, but rather correlated and/or decision-dependent. This resurgence of 
 interest stems from its widespread application in contemporary domains\, s
 uch as reinforcement learning\, performative prediction\, and fine-tuning 
 of large language models (LLMs). This presentation focuses on SA algorithm
 s applied to stochastic…
DTSTART;TZID=America/Vancouver:20241213T100000
DTEND;TZID=America/Vancouver:20241213T110000
LAST-MODIFIED:20241206T225452Z
LOCATION:UBC Vancouver Campus\, ICCS 288
SUMMARY:Stochastic Approximation Algorithms with Decision-Dependent Data: T
 he Case of Performative Prediction - Hoi-To Wai\, Assistant Professor\, CU
 HK
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/stochastic-approximation-algorithms-decision
 -dependent-data-case-performative-prediction-hoi
END:VEVENT
END:VCALENDAR