Solving Statistical Mechanics Using Variational Autoregressive Networks
This provides a general framework for physicists to compute variational free energy, estimate physical quantities, and generate uncorrelated samples more effectively than prior variational mean-field methods.
The authors tackled the problem of solving statistical mechanics for finite systems by extending variational mean-field approaches with autoregressive neural networks, achieving advantages over existing methods on classic systems like 2D Ising and Sherrington-Kirkpatrick models.
We propose a general framework for solving statistical mechanics of systems with finite size. The approach extends the celebrated variational mean-field approaches using autoregressive neural networks, which support direct sampling and exact calculation of normalized probability of configurations. It computes variational free energy, estimates physical quantities such as entropy, magnetizations and correlations, and generates uncorrelated samples all at once. Training of the network employs the policy gradient approach in reinforcement learning, which unbiasedly estimates the gradient of variational parameters. We apply our approach to several classic systems, including 2D Ising models, the Hopfield model, the Sherrington-Kirkpatrick model, and the inverse Ising model, for demonstrating its advantages over existing variational mean-field methods. Our approach sheds light on solving statistical physics problems using modern deep generative neural networks.