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:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
TZNAME:EET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Helsinki:20250127T140000
DTEND;TZID=Europe/Helsinki:20250127T153000
DTSTAMP:20260710T092513
CREATED:20250124T064125Z
LAST-MODIFIED:20250124T064125Z
UID:17818-1737986400-1737991800@crest.science
SUMMARY:Judith ROUSSEAU (Université Paris-Dauphine) - Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
DESCRIPTION:Statistical Seminar: Every Monday at 2:00 pm.\nTime: 2:00 pm – 3:00 pm\nDate: January 27th\nPlace: 3001 \nJudith ROUSSEAU (Université Paris-Dauphine) – Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions \n Abstract:  \nDenoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image\, audio and video generation as well as many more applications in science and beyond. The \textit{manifold hypothesis} states that high-dimensional data often lie on lower-dimensional manifolds within an ambient space of large dimension D \, and is widely believed to hold in provided examples. While recent results have provided invaluable insight into how diffusion models adapt to the manifold hypothesis\, they do not capture the great empirical success of these models. \nIn this work\, we study DDPMs under the manifold hypothesis and prove that they achieve rates independent of the ambient dimension in terms of learning the score. In terms of sampling\, we obtain rates independent of the ambient dimension w.r.t.\ the Kullback-Leibler divergence\, and $O(\sqrt{D})$ w.r.t.\ the Wasserstein distance. We do this by developing a new framework connecting diffusion models to the well-studied theory of extrema of Gaussian Processes. \nThis is a joint work with I. Azangulov and G. Deligliannidis (Univ of Oxford) \nOrganizers: \nAnna KORBA (CREST)\, Karim LOUNICI (CMAP) \, Jaouad MOURTADA (CREST) \nSponsors:\nCREST-CMAP \n
URL:https://crest.science/event/judith-rousseau-universite-paris-dauphine-convergence-of-diffusion-models-under-the-manifold-hypothesis-in-high-dimensions/
CATEGORIES:Seminars,Statistics
ATTACH;FMTTYPE=:
END:VEVENT
END:VCALENDAR