Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo

Holden Lee; Andrej Risteski; Rong Ge

NeurIPS 2018poster53 citations

Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo

Abstract

A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). One prevalent example of this is sampling posteriors in parametric distributions, such as latent-variable generative models. However sampling (even very approximately) can be #P-hard.

BibTeX

@inproceedings{NEURIPS2018_c6ede20e,
 author = {Lee, Holden and Risteski, Andrej and Ge, Rong},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/c6ede20e6f597abf4b3f6bb30cee16c7-Paper.pdf},
 volume = {31},
 year = {2018}
}