BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:31393263-6562-4633-b962-383630383065
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Nonconvex Stochastic Nested Optimization - Saeed Ghadimi\, Ass
 istant Professor\, University of Waterloo.
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20230312T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20201101T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20211107T020000
RDATE:20221106T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20210314T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20220313T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:935bb11b-98f3-4f5b-a37f-ad24960b6384
DTSTAMP:20260416T182259Z
CLASS:PUBLIC
CREATED:20210525T215145Z
DESCRIPTION:Please register for this event here. Abstract: In this talk\, I
  present a class of stochastic optimization problems in which the objectiv
 e function is a composition of two or more expectations. This class of pro
 blems arises in several applications such as low-rank matrix estimation\, 
 policy evaluation for Markov decision processes\, and compressed sensing. 
 I will first present a Nested Averaging Stochastic Approximation (NASA) al
 gorithm for solving this non-classical optimization problem when the objec
 tive function is a composition of two functions and show that it achieves 
 the well-known sample…
DTSTART;TZID=America/Vancouver:20210607T120000
DTEND;TZID=America/Vancouver:20210607T130000
LAST-MODIFIED:20210525T220124Z
LOCATION:Please register to receive the Zoom link
SUMMARY:Nonconvex Stochastic Nested Optimization - Saeed Ghadimi\, Assistan
 t Professor\, University of Waterloo.
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/nonconvex-stochastic-nested-optimization-sae
 ed-ghadimi-assistant-professor-university
END:VEVENT
END:VCALENDAR