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:20260413T140000
DTEND;TZID=Europe/Helsinki:20260413T153000
DTSTAMP:20260709T193832
CREATED:20260223T092343Z
LAST-MODIFIED:20260330T122334Z
UID:18821-1776088800-1776094200@crest.science
SUMMARY:Hugo LAVENANT (Bocconi University)- Masked diffusions: how to choose an optimal schedule and how much is gained ?
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: 13th April\nPlace: 3001 \n  \nHugo LAVENANT (Bocconi University)- Masked diffusions: how to choose an optimal schedule and how much is gained ? \n \n  \n Abstract:  \n  \nWe look at the computational error made in the generation phase of Masked Diffusion Models\, which were recently proposed for generative modelling of discrete data. These models make approximations of conditional dependence to speed up generation of new samples at the price of some bias in the sampling distribution. We explain how these models can be simply described once you do not try to make a parallel with continuous diffusion models. From this elementary description\, we study the resulting computation-vs-accuracy trade-off\, providing general error bounds in relative entropy\, and we investigate the gains obtained by using non-constant schedule sizes. \nThis is joint work with Giacomo Zanella. \n  \nOrganizers: \nAnna KORBA (CREST)\, Vincent DIVOL (CREST) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/hugo-lavenant-bocconi-university-tba/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR