BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:65623862-3735-4233-b264-396538623363
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Overcoming Mode Collapse and the Curse of Dimensionality - Ke 
 Li\, Assistant Professor\, Simon Fraser University
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20221106T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20201101T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20211107T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20200308T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20210314T020000
RDATE:20220313T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:eebe91da-2f28-4970-9a9a-583d96c18499
DTSTAMP:20260501T043440Z
CLASS:PUBLIC
CREATED:20201119T234021Z
DESCRIPTION:Please register for this event here. Abstract: In this talk\, I
  will present our work on overcoming two long-standing problems in machine
  learning: 1. Mode collapse in generative adversarial nets (GANs) Generati
 ve adversarial nets (GANs) are perhaps the most popular class of generativ
 e models in use today. Unfortunately\, they suffer from the well-documente
 d problem of mode collapse\, which the many successive variants of GANs ha
 ve failed to overcome. I will illustrate why mode collapse happens fundame
 ntally and show a simple way to overcome it\, which is the basis of a new 
 method known as…
DTSTART;TZID=America/Vancouver:20201202T150000
DTEND;TZID=America/Vancouver:20201202T160000
LAST-MODIFIED:20210610T230100Z
LOCATION:Please register to receive the Zoom link
SUMMARY:Overcoming Mode Collapse and the Curse of Dimensionality - Ke Li\, 
 Assistant Professor\, Simon Fraser University
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/overcoming-mode-collapse-and-curse-dimension
 ality-ke-li-assistant-professor-simon-fraser
END:VEVENT
END:VCALENDAR