Self-learning Monte Carlo method with Behler-Parrinello neural networks

TL;DR

This paper introduces a novel approach combining Behler-Parrinello neural networks with Self-learning Monte Carlo to efficiently model many-body interactions, significantly improving acceptance ratios in quantum impurity simulations.

Contribution

It presents the first integration of BPNNs as effective Hamiltonians in SLMC, enabling modeling of complex many-body interactions without prior explicit forms.

Findings

Acceptance ratio improved from 0.01 to 0.76 using BPNN

BPNN captures many-body interactions omitted in explicit forms

Enhanced efficiency of SLMC in quantum impurity models

Abstract

We propose a general way to construct an effective Hamiltonian in the Self-learning Monte Carlo method (SLMC), which speeds up Monte Carlo simulations by training an effective model to propose uncorrelated configurations in the Markov chain. Its applications are, however, limited. This is because it is not obvious to find the explicit form of the effective Hamiltonians. Particularly, it is difficult to make trainable effective Hamiltonians including many-body interactions. In order to overcome this critical difficulty, we introduce the Behler-Parrinello neural networks (BPNNs) as "effective Hamiltonian'' without any prior knowledge, which is used to construct the potential-energy surfaces in interacting many particle systems for molecular dynamics. We combine SLMC with BPNN by focusing on a divisibility of Hamiltonian and propose how to construct the element-wise configurations. We apply it to quantum impurity models. We observed significant improvement of the acceptance ratio from 0.01 (the effective Hamiltonian with the explicit form) to 0.76 (BPNN). This drastic improvement implies that the BPNN effective Hamiltonian includes many body interaction, which is omitted in the effective Hamiltonian with the explicit forms. The BPNNs make SLMC more promising.