BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Economics | IP Paris - ECPv5.1.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Economics | IP Paris
X-ORIGINAL-URL:https://econ.ip-paris.fr
X-WR-CALDESC:Events for Department of Economics | IP Paris
BEGIN:VTIMEZONE
TZID:Europe/Helsinki
BEGIN:DAYLIGHT
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20251124T140000
DTEND;TZID=Europe/Helsinki:20251124T150000
DTSTAMP:20260409T091912
CREATED:20251126T093831Z
LAST-MODIFIED:20251126T093843Z
UID:15930-1763992800-1763996400@econ.ip-paris.fr
SUMMARY:Antonio OCELLO (CREST)  "Convergence Analysis of Diffusion Models: Towards Reliable Sampling"
DESCRIPTION:Statistics\nTime: 2.00 p.m.\nDate: 24th November 2025\nRoom 3001 \nAntonio OCELLO (Ecole Polytechnique) “Convergence Analysis of Diffusion Models: Towards Reliable Sampling” \nAbstract : \nGenerative models are attracting growing attention across various applied domains\, including insurance and finance. Their potential lies in their capacity to capture and reproduce complex data patterns\, crucial for realistic modeling and decision-making under uncertainty. Among the available methods\, Score-Based Generative Models (SGMs)\, also known as diffusion models\, offer a flexible framework to sample from complex\, high-dimensional distributions. However\, a key challenge lies in rigorously understanding their convergence. \nIn this talk\, I will present recent advances in the theoretical analysis of SGMs. First\, I will provide explicit bounds on Wasserstein-2 distance under the log-concave assumption of the target data distribution. Second\, I will generalize this bound beyond the log-concave settings—such as for mixtures of Gaussians. \nThis talk is based on joint work with Stanislas Strasman\, Claire Boyer\, Sylvain Le Corff\, and Vincent Lemaire (TMLR 2024 – https://openreview.net/forum?id=BlYIPa0Fx1)\, as well as a recent collaboration with Marta Gentiloni-Silveri (ICML 2025 – https://arxiv.org/pdf/2501.02298). \n  \nOrganizers:  Jaouad MOURTADA\, Anna KORBA\, Vincent DIVOL \n  \n
URL:https://econ.ip-paris.fr/event/antonio-ocello-ecole-polytechnique-convergence-analysis-of-diffusion-models-towards-reliable-sampling-2/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR