BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:31656463-3262-4964-b038-666331336365
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Ensembles in the Age of Overparameterization: Promises and Pat
 hologies - Geoff Pleiss\, Assistant Professor\, UBC
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20261101T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20231105T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20241103T020000
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:d192f8e9-fc7f-43b2-9414-a3c22e89d7da
DTSTAMP:20260306T065842Z
CLASS:PUBLIC
CREATED:20241016T225047Z
DESCRIPTION:Zoom Link Abstract: Ensemble methods have historically used eit
 her high-bias base learners (e.g. through boosting) or high-variance base 
 learners (e.g. through bagging). Modern neural networks cannot be understo
 od through this classic bias-variance tradeoff\, yet 'deep ensembles' are 
 pervasive in safety-critical and high-uncertainty application domains. Thi
 s talk will cover surprising and counterintuitive phenomena that emerge wh
 en ensembling overparameterized base models like neural networks. While de
 ep ensembles improve generalization in a simple and cost-effective manner\
 , their accuracy and…
DTSTART;TZID=America/Vancouver:20241023T110000
DTEND;TZID=America/Vancouver:20241023T120000
LAST-MODIFIED:20241017T211532Z
LOCATION:UBC Vancouver Campus\, ICCS X836 / Please register to receive Zoom
  link
SUMMARY:Ensembles in the Age of Overparameterization: Promises and Patholog
 ies - Geoff Pleiss\, Assistant Professor\, UBC
TRANSP:OPAQUE
URL:https://caida.ubc.ca/index.php/event/ensembles-age-overparameterization
 -promises-and-pathologies-geoff-pleiss-assistant-professor
END:VEVENT
END:VCALENDAR