BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:34396638-3833-4963-a539-353833333631
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:CVL Talk: Rethinking classical optimization in Graphics - Mich
 ael Fischer\, UCL
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20250309T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20221106T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20231105T020000
RDATE:20241103T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20230312T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20240310T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:2ce44187-bee9-441f-99c6-cd43b9be1e3a
DTSTAMP:20260223T042000Z
CLASS:PUBLIC
CREATED:20230614T222341Z
DESCRIPTION:Abstract: Gradient-based optimization has become the de-facto s
 tandard for optimization in the Graphics community. However\, it is rarely
  questioned whether we can do “better” than simple gradient descent (GD) -
  in fact\, it is easy to construct examples where GD is easily outperforme
 d by other methods. This talk will explore two such scenarios: Firstly\, w
 e will use meta-learning to optimize over GD itself\, leading to improved 
 convergence and insights for data sampling in appearance reproduction scen
 arios. Secondly\, we will replace the traditional (and sometimes uninforma
 tive and brittle)…
DTSTART;TZID=America/Vancouver:20230616T110000
DTEND;TZID=America/Vancouver:20230616T120000
LAST-MODIFIED:20230615T174633Z
LOCATION:UBC Vancouver Campus\, ICCS X836
SUMMARY:CVL Talk: Rethinking classical optimization in Graphics - Michael F
 ischer\, UCL
TRANSP:OPAQUE
URL:https://caida.ubc.ca/index.php/event/cvl-talk-rethinking-classical-opti
 mization-graphics-michael-fischer-ucl
END:VEVENT
END:VCALENDAR