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

06/26/2019
by   Feng Pan, et al.
0

We propose a general method for solving statistical mechanics problems defined on sparse graphs, such as random graphs, real-world networks, and low-dimensional lattices. Our approach extract a small feedback vertex set of the sparse graph, converting the sparse system to a strongly correlated system with many-body and dense interactions on the feedback set, then solve it using variational method based on neural networks to estimate free energy, observables, and generate unbiased samples via direct sampling. Extensive experiments show that our approach is more accurate than existing approaches for sparse spin glass systems. On random graphs and real-world networks, our approach significantly outperforms the standard methods for sparse systems such as belief-propagation; on structured sparse systems such as two-dimensional lattices our approach is significantly faster and more accurate than recently proposed variational autoregressive networks using convolution neural networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/27/2018

Solving Statistical Mechanics using Variational Autoregressive Networks

We propose a general framework for solving statistical mechanics of syst...
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
06/13/2019

Spaceland Embedding of Sparse Stochastic Graphs

We introduce a nonlinear method for directly embedding large, sparse, st...
research
08/09/2021

Knowledge accumulating: The general pattern of learning

Artificial Intelligence has been developed for decades with the achievem...
research
02/19/2020

Neural Networks on Random Graphs

We performed a massive evaluation of neural networks with architectures ...
research
03/21/2022

Hierarchical autoregressive neural networks for statistical systems

It was recently proposed that neural networks could be used to approxima...
research
12/09/2022

Simulating first-order phase transition with hierarchical autoregressive networks

We apply the Hierarchical Autoregressive Neural (HAN) network sampling a...

Please sign up or login with your details

Forgot password? Click here to reset