Comment on "Solving Statistical Mechanics Using VANs": Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling
Statistical Mechanics
2019-03-27 v1 Machine Learning
Machine Learning
Abstract
In this comment on "Solving Statistical Mechanics Using Variational Autoregressive Networks" by Wu et al., we propose a subtle yet powerful modification of their approach. We show that the inherent sampling error of their method can be corrected by using neural network-based MCMC or importance sampling which leads to asymptotically unbiased estimators for physical quantities. This modification is possible due to a singular property of VANs, namely that they provide the exact sample probability. With these modifications, we believe that their method could have a substantially greater impact on various important fields of physics, including strongly-interacting field theories and statistical physics.
Cite
@article{arxiv.1903.11048,
title = {Comment on "Solving Statistical Mechanics Using VANs": Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling},
author = {Kim Nicoli and Pan Kessel and Nils Strodthoff and Wojciech Samek and Klaus-Robert Müller and Shinichi Nakajima},
journal= {arXiv preprint arXiv:1903.11048},
year = {2019}
}
Comments
6 pages, 4 figures