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:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20240304T120000
DTEND;TZID=Europe/Helsinki:20240304T140000
DTSTAMP:20260710T204816
CREATED:20240304T170557Z
LAST-MODIFIED:20240304T170557Z
UID:16756-1709553600-1709560800@crest.science
SUMMARY:Séminaire Palaisien
DESCRIPTION:REGISTER05 Mar 2024\, 12h At Inria – Salle Gilles Kahn\n\n\n\nAustin Stromme – Minimum intrinsic dimension scaling for entropic optimal transport\n \n\nEntropic optimal transport (entropic OT) is a regularized variant of the optimal transport problem\, widely used in practice for its computational benefits. A key statistical question for both entropic and un-regularized OT is the extent to which low-dimensional structure\, of the type conjectured by the well-known manifold hypothesis\, affects the statistical rates of convergence. In this talk\, we will present statistical results for entropic OT which clarify the statistical role of…\n\n\n\nBadr-Eddine Cherief Abdellatif – A PAC-Bayes perspective on learning and generalization\n \n\nBorn in the late 20th century\, PAC-Bayes has recently re-emerged as a powerful framework for learning with guarantees. Its bounds offer a principled way to understand the generalization ability of randomized learning algorithms\, even guiding the design of new ones. This introduction dives into the foundations of PAC-Bayes\, explores its recent advancements\, and tries to offer some insights into promising future research directions.\n\n\n\n
URL:https://crest.science/event/seminaire-palaisien-3/
LOCATION:INRIA – Salle Gilles Kahn
CATEGORIES:Conferences and Workshops,Statistics
END:VEVENT
END:VCALENDAR