English

Recurrent Neural Network Wave Functions

Disordered Systems and Neural Networks 2020-07-01 v4 Strongly Correlated Electrons Computational Physics Quantum Physics

Abstract

A core technology that has emerged from the artificial intelligence revolution is the recurrent neural network (RNN). Its unique sequence-based architecture provides a tractable likelihood estimate with stable training paradigms, a combination that has precipitated many spectacular advances in natural language processing and neural machine translation. This architecture also makes a good candidate for a variational wave function, where the RNN parameters are tuned to learn the approximate ground state of a quantum Hamiltonian. In this paper, we demonstrate the ability of RNNs to represent several many-body wave functions, optimizing the variational parameters using a stochastic approach. Among other attractive features of these variational wave functions, their autoregressive nature allows for the efficient calculation of physical estimators by providing independent samples. We demonstrate the effectiveness of RNN wave functions by calculating ground state energies, correlation functions, and entanglement entropies for several quantum spin models of interest to condensed matter physicists in one and two spatial dimensions.

Keywords

Cite

@article{arxiv.2002.02973,
  title  = {Recurrent Neural Network Wave Functions},
  author = {Mohamed Hibat-Allah and Martin Ganahl and Lauren E. Hayward and Roger G. Melko and Juan Carrasquilla},
  journal= {arXiv preprint arXiv:2002.02973},
  year   = {2020}
}

Comments

The GitHub link to the open-source code is fixed

R2 v1 2026-06-23T13:34:41.497Z