University of Cambridge > > ML@CL Seminar Series > Theoretical guarantees for sampling and inference in generative models with latent diffusions

Theoretical guarantees for sampling and inference in generative models with latent diffusions

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

If you have a question about this talk, please contact Francisco Vargas.


Talk is based on this paper.


We introduce and study a class of probabilistic generative models, where the latent object is a finite-dimensional diffusion process on a finite time interval and the observed variable is drawn conditionally on the terminal point of the diffusion. We make the following contributions: We provide a unified viewpoint on both sampling and variational inference in such generative models through the lens of stochastic control. We quantify the expressiveness of diffusion-based generative models. Specifically, we show that one can efficiently sample from a wide class of terminal target distributions by choosing the drift of the latent diffusion from the class of multilayer feedforward neural nets, with the accuracy of sampling measured by the KullbackÔÇôLeibler divergence to the target distribution. Finally, we present and analyze a scheme for unbiased simulation of generative models with latent diffusions and provide bounds on the variance of the resulting estimators. This scheme can be implemented as a deep generative model with a random number of layers.


Part of ML@CL Seminar Series in topics relevant to machine learning and statistics.

Meeting ID: 966 8293 0826

Passcode: 007922

This talk is part of the ML@CL Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity