Seminar

2025 Constance van Eeden Seminar: Dr. Arnaud Doucet

This event is being hosted by the Department of Statistics at UBC.

Invited Speaker: Dr. Arnaud Doucet, Senior Staff Research Scientist at Google DeepMind

Title: From Diffusion Models to Schrödinger Bridges - When Generative Modeling Meets Optimal Transport

Event Date: Friday, April 4th, 2025 - 10:30 am to 12:00 pm PT

Location: Online or ESB 5104/5106 at the University of British Columbia

Event Registration: https://forms.gle/gkeoLAr9MwoCvnar6 

(If you have any questions about your registration or about the seminar, please contact headsec@stat.ubc.ca)

Abstract:

Denoising diffusion models have revolutionized generative modeling. Conceptually, these methods define a transport mechanism from a noise distribution to a data distribution. Recent advancements have extended this framework to define transport maps between arbitrary distributions, significantly expanding the potential for unpaired data translation. However, existing methods often fail to approximate optimal transport maps, which are theoretically known to possess advantageous properties. In this talk, we will show how one can modify current methodologies to compute Schrödinger bridges—an entropy-regularized variant of dynamic optimal transport. We will demonstrate this methodology on a variety of unpaired data translation tasks.
 

van Eeden Speaker:

Dr. Arnaud Doucet has been invited to be this year’s van Eeden speaker by the graduate students in the Department of Statistics at the University of British Columbia. A van Eeden speaker is a prominent statistician who is chosen each year to give a lecture, supported by the UBC Constance van Eeden Fund. 

The 2025 seminar is additionally sponsored by the Canadian Statistical Sciences Institute (CANSSI), the Pacific Institute for the Mathematical Sciences (PIMS), and the Walter H. Gage Memorial Fund.