Dissipation and Optimal Transport in Discrete and Continuous Flow-based Models

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

• Grant M. Rotskoff (U Stanford)
• Tuesday 13 May 2025, 13:00-14:00
• Center for Mathematical Sciences, Lecture room MR4.

If you have a question about this talk, please contact Sarah Loos.

In this talk, I will discuss connections between control problems that arise in nonequilibrium statistical physics and generative models to illustrate how tools built for low dissipation control and rare event sampling can be leveraged to improve sample efficiency in flow-based generative models. Employing these notions, I will outline a strategy for parameterizing discrete diffusion models using tensor networks, which improves MCMC in some simple models from statistical mechanics. Going beyond this approach, I will discuss “mixed-resolution” discrete and continuous models we have been developing and how to build statistically controlled sampling schemes for these models.

This talk is part of the DAMTP Statistical Physics and Soft Matter Seminar series.

This talk is included in these lists:

• All CMS events
• Center for Mathematical Sciences, Lecture room MR4
• DAMTP Statistical Physics and Soft Matter Seminar
• Soft Matter
• bld31

Note that ex-directory lists are not shown.