University of Cambridge > Talks.cam > DAMTP Statistical Physics and Soft Matter Seminar > Dissipation and Optimal Transport in Discrete and Continuous Flow-based Models

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

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

Download to your calendar using vCal

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:

Note that ex-directory lists are not shown.

Other lists

MAB 104, Mary Allan Building, Homerton College, Hills Road, Cambridge CB2 8PQ Cambridge Judge Business School (http://www.jbs.cam.ac.uk/aboutus/location.html) Pavillion Room, Hughes Hall, Cambridge

Other talks

Machine Learning for Spectral Geometry and Vice Versa title abstract tba Spectral theory for Dirac operators with singular potentials Tea and Coffee Break Title to be confirmed Fun experiments you can only do with frogs
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity