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:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20201101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:68326d89f13da
DTSTART;TZID=America/Toronto:20210625T153000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20210625T153000
URL:/combinatorics-and-optimization/events/tutte-colloq
 uium-dmitriy-drusvyatskiy
SUMMARY:Tutte Colloquium - Dmitriy Drusvyatskiy
CLASS:PUBLIC
DESCRIPTION:Summary \n\nTITLE: From low probability to high confidenc
 e in stochastic convex optimization\n\nSpeaker:\n Dmitriy Drusvyatskiy
 \n\nAffliliation:\n University of Washington\n\nZoom:\n Contact Emma Wats
 on\n\nABSTRACT:\n\nStandard results in stochastic convex optimization boun
 d the number of\nsamples that an algorithm needs to generate a point with 
 small\nfunction value in expectation. More nuanced high probability\nguara
 ntees are rare\, and typically either rely on “light-tail”\nnoise assu
 mptions or exhibit worse sample complexity. In this work\, we\nshow that a
  wide class of stochastic optimization algorithms can be\naugmented with h
 igh confidence bounds at an overhead cost that is only\nlogarithmic in the
  confidence level and polylogarithmic in the\ncondition number.\n 
DTSTAMP:20250525T010825Z
END:VEVENT
END:VCALENDAR