BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:682e3de2c7299
DTSTART;TZID=America/Toronto:20231124T130000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20231124T130000
URL:/combinatorics-and-optimization/events/co-reading-g
 roup-victor-sanches-portella
SUMMARY:C&O Reading Group - Victor Sanches Portella
CLASS:PUBLIC
DESCRIPTION:Summary \n\nTITLE: Online Convex Optimization\n\nSPEAKER:\n Vic
 tor Sanches Portella\n\nAFFILIATION:\n University of British Columbia\n\nL
 OCATION:\n MC 6029\n\nABSTRACT: Online learning (OL) is a theoretical fram
 ework for learning\nwith data online. Moreover\, we usually make no assump
 tions on the\ndistribution of the data\, allowing it even to be adversaria
 l to the\nlearner. Maybe surprisingly\, we can still design algorithms tha
 t\, in\nsome sense\, “successfully learn” in this setting. This level 
 of\ngenerality makes many of the ideas\, algorithms\, and techniques from 
 OL\nuseful in applications in theoretical computer science\, optimization\
 nin machine learning\, and control. In this talk I will give a brief\nintr
 oduction to the key concepts in online learning and  mention a\nfew topic
 s within or adjacent to online learning that I believe cover\nfundamental 
 ideas in OL and/or with interesting open research\nquestions.\n 
DTSTAMP:20250521T205602Z
END:VEVENT
END:VCALENDAR