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:69e344b2422cd
DTSTART;TZID=America/Toronto:20240517T153000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20240517T163000
URL:https://uwaterloo.ca/combinatorics-and-optimization/events/distinguishe
 d-tutte-lecture-katya-scheinberg
SUMMARY:Distinguished Tutte Lecture - Katya Scheinberg
CLASS:PUBLIC
DESCRIPTION:TITLE: Stochastic  Oracles and Where to Find Them\n\nSPEAKER:
 \n Katya Scheinberg\n\nAFFILIATION:\n Cornell University\n\nLOCATION:\n MC
  5501\n\nABSTRACT: Continuous optimization is a mature field\, which has\
 nrecently undergone major expansion and change. One of the key new\ndirect
 ions is the development of methods that do not require exact\ninformation 
 about the objective function. Nevertheless\, the majority\nof these method
 s\, from stochastic gradient descent to \"zero-th order\"\nmethods use som
 e kind of approximate first order information. We will\noverview different
  methods of obtaining this information\, including\nsimple stochastic grad
 ient via sampling\, robust gradient estimation in\nadversarial settings\, 
 traditional and randomized finite difference\nmethods and more. \n\nWe wil
 l discuss what key properties of these inexact\, stochastic first\norder o
 racles are useful for convergence analysis of optimization\nmethods that u
 se them. 
DTSTAMP:20260418T084538Z
END:VEVENT
END:VCALENDAR