BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:38396464-3531-4138-a635-653736326432
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Memory-augmented Optimizers for Deep Learning and Lifelong Lea
 rning - Sarath Chandar\, Assistant Professor\, Polytechnique Montreal
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20251102T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20231105T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20241103T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20230312T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20240310T020000
RDATE:20250309T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:6726e7ff-d3dd-40ee-b270-69031eb8a33c
DTSTAMP:20260306T055235Z
CLASS:PUBLIC
CREATED:20240209T225608Z
DESCRIPTION:Zoom Link Abstract: In this talk\, I will introduce the idea of
  adding external memory to standard optimization methods to improve their 
 performance in deep learning and lifelong learning. In the first part of t
 his talk\, I will focus on general deep learning problems and I will intro
 duce a new family of critical gradient-based optimizers. Such optimizers r
 etain a limited view of their gradient history in their internal memory an
 d scale well to large real-life datasets. Our experiments show that the pr
 oposed memory-augmented extensions of standard optimizers enjoy accelerate
 d convergence and…
DTSTART;TZID=America/Vancouver:20240226T100000
DTEND;TZID=America/Vancouver:20240226T110000
LAST-MODIFIED:20240221T225525Z
LOCATION:UBC Vancouver Campus\, ICCS X836
SUMMARY:Memory-augmented Optimizers for Deep Learning and Lifelong Learning
  - Sarath Chandar\, Assistant Professor\, Polytechnique Montreal
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/memory-augmented-optimizers-deep-learning-an
 d-lifelong-learning-sarath-chandar-assistant
END:VEVENT
END:VCALENDAR