Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2002.02973 · Physical Review Research

Recurrent neural network wave functions

Mohamed Hibat-Allah, Martin Ganahl, Lauren E. Hayward Sierens, Roger G. Melko, Juan Carrasquilla

Published Jun 17, 2020• 274 citations
arXivHTMLPDF

Abstract

This paper introduces a new class of computationally tractable wavefunctions, called recurrent neural network wavefunctions, based on recurrent neural network technology. The authors show that these wavefunctions outperform optimization methods for strongly correlated many-body systems with less variational parameters.
DOI
10.1103/physrevresearch.2.023358

Related papers

Optimizing Neural Network Wavefunctions Using Variational Monte Carlo with Evolution Strategies

Mykhailo Moroz, O. V. Bovgyra

Obtaining accurate solutions to many-electron quantum systems is of critical importance, in principle, such solutions allow computing most of possible chemical and physical properties from first principles. Exact solutions require utilizing exponentially scaling algorithms, which are not practical for large systems. Neural networks provide a new approach to approximating the solution while keeping a high level of accuracy. In this work, we explore a novel method of optimizing neural network wavefunctions by employing Evolution Strategies (ES) within a Variational Monte Carlo (VMC) framework. This allows us to more robustly find solutions while keeping a small number of parameters, making it an efficient alternative to traditional methods.

IEEE International Conference on Electronics and Information Technologies (ELIT)•Sep 26, 2023•0 citations

Optimization of neural network wave functions in variational Monte Carlo

Yuyang Wang, Xin Liu

The central challenge in materials science and quantum chemistry is solving the electronic Schrodinger equation, complicated by the curse of dimensionality as system size grows. Neural network-based variational Monte Carlo (NN-VMC) offers a promising path forward, achieving unprecedented accuracy at far lower cost than traditional high-level methods. However, the flexibility of neural network wavefunctions introduces a bottleneck: their optimization is high-dimensional, stochastic, and non-convex. This Perspective reviews the evolution of optimization methods in NN-VMC, from stochastic reconfiguration to approximate second-order algorithms and geometric insights. We highlight key challenges currently limiting scalability and efficiency, and outline future opportunities to advance the field. With continued progress in optimization, neural network techniques, and computer architectures, NN-VMC can tackle larger and more complex quantum systems and move from trailing experiments to guiding them.

The Innovation Informatics•Nov 27, 2025•1 citation

Quantum machine learning of molecular energies with hybrid quantum-neural wavefunction

Weitang Li, Shi‐Xin Zhang, Zirui Sheng +3 more

The combination of quantum circuits and neural networks allows efficient quantum machine learning of molecular wavefunction.

arXiv:2501.04264•Digital Discovery•Jan 1, 2025•4 citations

Quantum Geometric Tensor Preconditioning for Stable Training of Recurrent Neural Quantum States

Adil Attar, Amine M. Aboussalah, Mohamed Hibat-Allah

Neural Quantum States (NQS) provide a powerful neural network-based variational framework for representing many-body wave functions and solving for ground states. Recurrent Neural Networks (RNNs) are particularly promising owing to their relatively low computational cost and their autoregressive property, which enables perfect sampling. Recently, RNNs have been reported to be unstable under curvature-based optimizers such as the minimum-step stochastic reconfiguration (minSR) method. In this paper, we address this perceived limitation and show that minSR can be stabilized through simple regularization techniques, enabling robust training of RNN-based NQS with only a few samples. Our approach outperforms the Adam optimizer on the one-dimensional transverse-field Ising model and the one-dimensional cluster state, and provides competitive results on the two-dimensional Heisenberg and $J_1-J_2$ models. This work offers a promising pathway for using modern optimization techniques with autoregressive NQS to address open questions in quantum simulation.

cond-mat.dis-nnCross-listedarXiv:2608.18065•Aug 19, 2026•0 citations

Ground states of planar dipolar rotor chains with recurrent neural networks

Tobias Serwatka, Pierre–Nicholas Roy

In this contribution, we employ a recurrent neural network (RNN) architecture in a variational optimization to obtain the ground state of linear chains of planar, dipolar rotors. We test different local basis sets and discuss their impact on the sign structure of the many-body ground state wavefunction. It is demonstrated that the RNN ansatz we employ is able to treat systems with and without a sign problem in the ground state. For larger chains with up to 50 rotors, accurate properties, such as correlation functions and Binder parameters, are calculated. By employing quantum annealing, we show that precise entanglement properties can be obtained. All these properties allow one to identify a quantum phase transition between a paraelectric and a ferroelectric quantum phase.

The Journal of Chemical Physics•Jun 10, 2024•4 citations

Learning the Ground State Wavefunction of Periodic Systems Using Recurrent Neural Networks

Christopher C. Roth, Allan H. MacDonald

Bulletin of the American Physical Society•Mar 5, 2020•0 citations
Obtaining accurate solutions to many-electron quantum systems is of critical importance, in principle, such solutions allow computing most of possible chemical and physical properties from first principles. Exact solutions require utilizing exponentially scaling algorithms, which are not practical for large systems. Neural networks provide a new approach to approximating the solution while keeping a high level of accuracy. In this work, we explore a novel method of optimizing neural network wavefunctions by employing Evolution Strategies (ES) within a Variational Monte Carlo (VMC) framework. This allows us to more robustly find solutions while keeping a small number of parameters, making it an efficient alternative to traditional methods.
The central challenge in materials science and quantum chemistry is solving the electronic Schrodinger equation, complicated by the curse of dimensionality as system size grows. Neural network-based variational Monte Carlo (NN-VMC) offers a promising path forward, achieving unprecedented accuracy at far lower cost than traditional high-level methods. However, the flexibility of neural network wavefunctions introduces a bottleneck: their optimization is high-dimensional, stochastic, and non-convex. This Perspective reviews the evolution of optimization methods in NN-VMC, from stochastic reconfiguration to approximate second-order algorithms and geometric insights. We highlight key challenges currently limiting scalability and efficiency, and outline future opportunities to advance the field. With continued progress in optimization, neural network techniques, and computer architectures, NN-VMC can tackle larger and more complex quantum systems and move from trailing experiments to guiding them.
Neural Quantum States (NQS) provide a powerful neural network-based variational framework for representing many-body wave functions and solving for ground states. Recurrent Neural Networks (RNNs) are particularly promising owing to their relatively low computational cost and their autoregressive property, which enables perfect sampling. Recently, RNNs have been reported to be unstable under curvature-based optimizers such as the minimum-step stochastic reconfiguration (minSR) method. In this paper, we address this perceived limitation and show that minSR can be stabilized through simple regularization techniques, enabling robust training of RNN-based NQS with only a few samples. Our approach outperforms the Adam optimizer on the one-dimensional transverse-field Ising model and the one-dimensional cluster state, and provides competitive results on the two-dimensional Heisenberg and J1−J2J_1-J_2J1​−J2​ models. This work offers a promising pathway for using modern optimization techniques with autoregressive NQS to address open questions in quantum simulation.
In this contribution, we employ a recurrent neural network (RNN) architecture in a variational optimization to obtain the ground state of linear chains of planar, dipolar rotors. We test different local basis sets and discuss their impact on the sign structure of the many-body ground state wavefunction. It is demonstrated that the RNN ansatz we employ is able to treat systems with and without a sign problem in the ground state. For larger chains with up to 50 rotors, accurate properties, such as correlation functions and Binder parameters, are calculated. By employing quantum annealing, we show that precise entanglement properties can be obtained. All these properties allow one to identify a quantum phase transition between a paraelectric and a ferroelectric quantum phase.