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:69d0d6faba170
DTSTART;TZID=America/Toronto:20231124T130000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20231124T130000
URL:https://uwaterloo.ca/combinatorics-and-optimization/events/co-reading-g
 roup-victor-sanches-portella
SUMMARY:C&O Reading Group - Victor Sanches Portella
CLASS:PUBLIC
DESCRIPTION:TITLE: Online Convex Optimization\n\nSPEAKER:\n Victor Sanches 
 Portella\n\nAFFILIATION:\n University of British Columbia\n\nLOCATION:\n M
 C 6029\n\nABSTRACT: Online learning (OL) is a theoretical framework for le
 arning\nwith data online. Moreover\, we usually make no assumptions on the
 \ndistribution of the data\, allowing it even to be adversarial to the\nle
 arner. Maybe surprisingly\, we can still design algorithms that\, in\nsome
  sense\, “successfully learn” in this setting. This level of\ngenerali
 ty makes many of the ideas\, algorithms\, and techniques from OL\nuseful i
 n applications in theoretical computer science\, optimization\nin machine 
 learning\, and control. In this talk I will give a brief\nintroduction to 
 the key concepts in online learning and  mention a\nfew topics within or 
 adjacent to online learning that I believe cover\nfundamental ideas in OL 
 and/or with interesting open research\nquestions.
DTSTAMP:20260404T091642Z
END:VEVENT
END:VCALENDAR