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:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:68a8d8c56c1cb
DTSTART;TZID=America/Toronto:20240517T153000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20240517T163000
URL:/combinatorics-and-optimization/events/distinguishe
 d-tutte-lecture-katya-scheinberg
SUMMARY:Distinguished Tutte Lecture - Katya Scheinberg
CLASS:PUBLIC
DESCRIPTION:Summary \n\nTITLE: Stochastic  Oracles and Where to Find Them
 \n\nSPEAKER:\n Katya Scheinberg\n\nAFFILIATION:\n Cornell University\n\nLO
 CATION:\n MC 5501\n\nABSTRACT: Continuous optimization is a mature field\
 , which has\nrecently undergone major expansion and change. One of the key
  new\ndirections is the development of methods that do not require exact\n
 information about the objective function. Nevertheless\, the majority\nof 
 these methods\, from stochastic gradient descent to \"zero-th order\"\nmet
 hods use some kind of approximate first order information. We will\novervi
 ew different methods of obtaining this information\, including\nsimple sto
 chastic gradient via sampling\, robust gradient estimation in\nadversarial
  settings\, traditional and randomized finite difference\nmethods and more
 . \n\nWe will discuss what key properties of these inexact\, stochastic fi
 rst\norder oracles are useful for convergence analysis of optimization\nme
 thods that use them. \n 
DTSTAMP:20250822T205325Z
END:VEVENT
END:VCALENDAR