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:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20260309T140000
DTEND;TZID=Europe/Helsinki:20260309T153000
DTSTAMP:20260709T203937
CREATED:20260223T090907Z
LAST-MODIFIED:20260305T110038Z
UID:18816-1773064800-1773070200@crest.science
SUMMARY:Aymeric DIEULEVEUT (Ecole Polytechnique) "Will computers replace optimization researchers?  Computer-aided proofs in first-order optimization\, a case study on error feedback."
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: 9th March\nPlace: 3001 \n  \nAymeric DIEULEVEUT (Ecole Polytechnique)  “Will computers replace optimization researchers? Computer-aided proofs in first-order optimization\, a case study on error feedback.” \n  \n Abstract: First-order methods are widely used in optimization and machine learning\, and their behavior often analyzed through the spectrum of worst case convergence rates. Obtaining such guarantees is often difficult and both time consuming and error-prone. Starting with the work of Drori and Teboulle (2014)\, novel techniques have been used to gain numerical insights\, leading to the release of various performance estimation (PE) software. \nIn this talk\, I will show how various computer-aided techniques can be used to study first-order optimization methods in a systematic way. From performance estimation problems with automated Lyapunov discovery\, to symbolic regression and computer algebra systems\, novel tools completely reshape the way we approach theory of optimization. \nAs a main example\, I will focus on error feedback methods used with compressed communication in distributed optimization. While error feedback has been widely studied\, existing theory often provides untight (thus unreliable) bounds. I will present tight analyses with matching lower bounds that allow a fair comparison between error feedback schemes and standard compressed gradient descent\, and help explain when error feedback is useful and when it is not. \n  \nOrganizers: \nAnna KORBA (CREST)\, Vincent DIVOL (CREST) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/aymeric-dieuleveut-ecole-polytechnique-tba/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR