Sampling using Diffusion Processes

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

• Dr Nicolas Macris, EPFL
• Wednesday 12 February 2025, 14:00-15:00
• MR5, CMS Pavilion A.

If you have a question about this talk, please contact Prof. Ramji Venkataramanan.

I will discuss a class of diffusion-based algorithms to draw samples from high-dimensional probability distributions given their unnormalized densities. Ideally, the method can transport samples from a Gaussian distribution to a specified target distribution in finite time. The stochastic interpolants framework used to derive a diffusion process, and also involves solving certain Hamilton-Jacobi-Bellman PDEs. These are solved using the theory of forward-backward stochastic differential equations (FBSDE) together with machine learning-based methods. Numerical experiments illustrating that the algorithm will also be discussed. This is joint work with Anand Jerry George.

This talk is part of the Information Theory Seminar series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Hanchen DaDaDash
• Information Theory Seminar
• Interested Talks
• MR5, CMS Pavilion A
• School of Physical Sciences
• Statistical Laboratory info aggregator
• bld31

Note that ex-directory lists are not shown.