From Diffusion Models to Schrödinger Bridges

Add to your list(s) Download to your calendar using vCal

• Professor Arnaud Doucet, University of Oxford
• Thursday 20 March 2025, 13:00-14:00
• Department of Engineering - LT1.

If you have a question about this talk, please contact Kimberly Cole.

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.

This talk is part of the Information Engineering Distinguished Lecture Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge University Engineering Department Talks
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Department of Engineering - LT1
• Featured lists
• Information Engineering Distinguished Lecture Series
• Information Engineering Division seminar list
• Interested Talks
• School of Technology
• Signal Processing and Communications Lab Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.