BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:62353231-6436-4535-a264-616133663161
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:The Non-Stochastic Control Framework -  Naman Agarwal\, Resear
 ch Scientist\, Google AI\, Princeton
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20221106T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20191103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20201101T020000
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:afae0404-15f8-4efb-843a-45f8be538260
DTSTAMP:20260227T085051Z
CLASS:PUBLIC
CREATED:20200918T214821Z
DESCRIPTION:Please register for this event here Abstract: Linear dynamical 
 systems are a continuous subclass of reinforcement learning models that ar
 e widely used in robotics\, finance\, engineering\, and meteorology. Class
 ical control\, has focused on dynamics with Gaussian i.i.d. Noise and quad
 ratic loss functions in terms of provably efficient algorithms. I will pre
 sent a non-stochastic control framework inspired by online learning\, that
  generalizes some traditional notions of robust control and discuss method
 ology which achieves efficient control with adversarial noise and general 
 convex loss functions…
DTSTART;TZID=America/Vancouver:20201005T140000
DTEND;TZID=America/Vancouver:20201005T150000
LAST-MODIFIED:20210610T230231Z
LOCATION:Please register to receive the Zoom link
SUMMARY:The Non-Stochastic Control Framework - Naman Agarwal\, Research Sci
 entist\, Google AI\, Princeton
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/non-stochastic-control-framework-naman-agarw
 al-research-scientist-google-ai-princeton
END:VEVENT
END:VCALENDAR