BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Optimal transport for generative diffusion modeling: bridging Schr
 ödinger and Bass - Huyen Pham (Ecole Polytechnique Paris)
DTSTART:20251112T105000Z
DTEND:20251112T113000Z
UID:TALK238492@talks.cam.ac.uk
DESCRIPTION:We study the problem of generating a continuous semimartingale
  that interpolates prescribed initial and terminal distributions. We cast 
 this task as an optimal transport problem on path space that bridges the S
 chr&ouml\;dinger bridge and the Bass martingale formulations\, yielding a 
 diffusion whose drift and volatility are jointly calibrated to data. We de
 rive an analytic characterization of the optimizer&mdash\;Schr&ouml\;dinge
 r&ndash\;Bridge&ndash\;Bass (SBB) diffusion&mdash\;and show that it admits
  a representation as a stretched Brownian motion under an explicit change 
 of measure. Building on this structure\, we develop a practical computatio
 nal scheme for SBB that is efficient and scalable\, providing a principled
  framework for generative diffusion modeling. We outline applications to i
 mage synthesis and time‑series generation\, highlighting SBB as a unifyi
 ng lens connecting entropic and martingale optimal transport in modern gen
 erative modeling.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR