Learning to Sample Better
Machine Learning
2023-10-18 v1 Machine Learning
Abstract
These lecture notes provide an introduction to recent advances in generative modeling methods based on the dynamical transportation of measures, by means of which samples from a simple base measure are mapped to samples from a target measure of interest. Special emphasis is put on the applications of these methods to Monte-Carlo (MC) sampling techniques, such as importance sampling and Markov Chain Monte-Carlo (MCMC) schemes. In this context, it is shown how the maps can be learned variationally using data generated by MC sampling, and how they can in turn be used to improve such sampling in a positive feedback loop.
Keywords
Cite
@article{arxiv.2310.11232,
title = {Learning to Sample Better},
author = {Michael S. Albergo and Eric Vanden-Eijnden},
journal= {arXiv preprint arXiv:2310.11232},
year = {2023}
}
Comments
Les Houches 2022 Summer School on Statistical Physics and Machine Learning