Poster
A-NICE-MC: Adversarial Training for MCMC
Jiaming Song · Shengjia Zhao · Stefano Ermon

Tue Dec 5th 06:30 -- 10:30 PM @ Pacific Ballroom #189 #None
in Posters Tue »

Existing Markov Chain Monte Carlo (MCMC) methods are either based on general-purpose and domain-agnostic schemes, which can lead to slow convergence, or require hand-crafting of problem-specific proposals by an expert. We propose A-NICE-MC, a novel method to train flexible parametric Markov chain kernels to produce samples with desired properties. First, we propose an efficient likelihood-free adversarial training method to train a Markov chain and mimic a given data distribution. Then, we leverage flexible volume preserving flows to obtain parametric kernels for MCMC. Using a bootstrap approach, we show how to train efficient Markov Chains to sample from a prescribed posterior distribution by iteratively improving the quality of both the model and the samples. A-NICE-MC provides the first framework to automatically design efficient domain-specific MCMC proposals. Empirical results demonstrate that A-NICE-MC combines the strong guarantees of MCMC with the expressiveness of deep neural networks, and is able to significantly outperform competing methods such as Hamiltonian Monte Carlo.

Keywords: Generative Models · MCMC · Unsupervised Learning · Adversarial Networks

Author Information

Jiaming Song (Stanford University)
Shengjia Zhao (Stanford University)
Stefano Ermon (Stanford)

More from the Same Authors