Solving Statistical Mechanics using Variational Autoregressive Networks

09/27/2018
by   Dian Wu, et al.
0

We propose a general framework for solving statistical mechanics of systems with a 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. The network 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 classical systems, including 2-d Ising models, Hopfield model, Sherrington--Kirkpatrick spin glasses, 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2019

Neural-network based general method for statistical mechanics on sparse systems

We propose a general method for solving statistical mechanics problems d...
research
03/26/2019

Comment on "Solving Statistical Mechanics Using VANs": Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling

In this comment on "Solving Statistical Mechanics Using Variational Auto...
research
10/29/2019

Asymptotically Unbiased Generative Neural Sampling

We propose a general framework for the estimation of observables with ge...
research
12/09/2022

Simulating first-order phase transition with hierarchical autoregressive networks

We apply the Hierarchical Autoregressive Neural (HAN) network sampling a...
research
09/24/2014

Variational Pseudolikelihood for Regularized Ising Inference

I propose a variational approach to maximum pseudolikelihood inference o...
research
02/16/2023

The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems

Generative Autoregressive Neural Networks (ARNN) have recently demonstra...
research
02/08/2018

Neural Network Renormalization Group

We present a variational renormalization group approach using deep gener...

Please sign up or login with your details

Forgot password? Click here to reset