BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CREST - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CREST
X-ORIGINAL-URL:https://crest.science
X-WR-CALDESC:Events for CREST
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20221030T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20221010T140000
DTEND;TZID=Europe/Helsinki:20221010T150000
DTSTAMP:20260711T133203
CREATED:20221005T074437Z
LAST-MODIFIED:20221005T074529Z
UID:14112-1665410400-1665414000@crest.science
SUMMARY:Yu Lu (CREST-ENSAE) "Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance"
DESCRIPTION:Statistical Seminar: Every Monday.\nTime: 2:00 pm\nDate: 10 of October 2022\nPlace: Room 3001 \nYu Lu (CREST-ENSAE) “Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance” \nAbstract:We study stochastic convex optimization under infinite noise variance. Specifically\, when the stochastic gradient is unbiased and has uniformly bounded (1 + κ)-th moment\, for some κ ∈ (0\, 1]\, we quantify the convergence rate of the Stochastic Mirror Descent algorithm with a particular class of uniformly convex mirror maps\, in terms of the number of iterations\, dimensionality and related geometric parameters of the optimization problem. Interestingly this algorithm does not require any explicit gradient clipping or normalization\, which have been extensively used in several recent empirical and theoretical works. We complement our convergence results with information-theoretic lower bounds showing that no other algorithm using only stochastic first-order oracles can achieve improved rates. Our results have several interesting consequences for devising online/streaming stochastic approximation algorithms for problems arising in robust statistics and machine learning. \n  \nOrganizers:\nCristina BUTUCEA (CREST)\, Alexandre TSYBAKOV (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST)\nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/shayn-mukherjee-university-of-leipzig-modeling-shapes-and-fields-2/
CATEGORIES:Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR