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:2109.12606 · Nature Machine Intelligence

Autoregressive neural-network wavefunctions for ab initio quantum chemistry

Thomas D. Barrett, Aleksei Malyshev, Alexander I. Lvovsky

Published Mar 31, 2022• 111 citations
arXivHTMLPDF
DOI
10.1038/s42256-022-00461-z

Related papers

Ab initio quantum chemistry with neural-network wavefunctions

Jan Hermann, JAMES M. SPENCER, Kenny Choo +5 more

arXiv:2208.12590•Nature Reviews Chemistry•Aug 9, 2023•169 citations

Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks

James S. Spencer, David Pfau, Alex Matthews +1 more

Bulletin of the American Physical Society•Mar 5, 2020•3 citations

Deterministic global optimization in ab-initio quantum chemistry

Pete P. Janes, Alistair P. L. Rendell

Journal of Global Optimization•Feb 13, 2012•3 citations

Transferable neural network quantum state method for quantum chemistry

Yangjun Wu, Jiexuan Zhou, Yumeng Zhou +2 more

Computer Physics Communications•Sep 23, 2026•0 citations

Retentive neural quantum states: efficient ansätze for ab initio quantum chemistry

Oliver Knitter, Dan Zhao, JAMES M. STOKES +3 more

Abstract Neural-network quantum states (NQS) has emerged as a powerful application of quantum-inspired deep learning for variational Monte Carlo methods, offering a competitive alternative to existing techniques for identifying ground states of quantum problems. A significant advancement toward improving the practical scalability of NQS has been the incorporation of autoregressive models, most recently transformers, as variational ansätze. Transformers learn sequence information with greater expressiveness than recurrent models, but at the cost of increased time complexity with respect to sequence length. We explore the use of the retentive network (RetNet), a recurrent alternative to transformers, as an ansatz for solving electronic ground state problems in ab initio quantum chemistry. Unlike transformers, RetNets overcome this time complexity bottleneck by processing data in parallel during training, and recurrently during inference. We give a simple computational cost estimate of the RetNet and directly compare it with similar estimates for transformers, establishing a clear threshold ratio of problem-to-model size past which the RetNet’s time complexity outperforms that of the transformer. Though this efficiency comes at the expense of decreased expressiveness relative to the transformer, we overcome this gap through training strategies that leverage the autoregressive structure of the model—namely, variational neural annealing. Our findings support the RetNet as a means of improving the time complexity of NQS without sacrificing accuracy. We provide further evidence that the ablative improvements of neural annealing extend beyond the RetNet architecture, suggesting it would serve as an effective general training strategy for autoregressive NQS.

arXiv:2411.03900•Machine Learning Science and Technology•Apr 10, 2025•4 citations

Neural network representations of quantum many-body states

Ying Zhen Yang, Huaixin Cao, Zhanjun Zhang

Science China Physics Mechanics and Astronomy•Jun 20, 2019•14 citations
Abstract Neural-network quantum states (NQS) has emerged as a powerful application of quantum-inspired deep learning for variational Monte Carlo methods, offering a competitive alternative to existing techniques for identifying ground states of quantum problems. A significant advancement toward improving the practical scalability of NQS has been the incorporation of autoregressive models, most recently transformers, as variational ansätze. Transformers learn sequence information with greater expressiveness than recurrent models, but at the cost of increased time complexity with respect to sequence length. We explore the use of the retentive network (RetNet), a recurrent alternative to transformers, as an ansatz for solving electronic ground state problems in ab initio quantum chemistry. Unlike transformers, RetNets overcome this time complexity bottleneck by processing data in parallel during training, and recurrently during inference. We give a simple computational cost estimate of the RetNet and directly compare it with similar estimates for transformers, establishing a clear threshold ratio of problem-to-model size past which the RetNet’s time complexity outperforms that of the transformer. Though this efficiency comes at the expense of decreased expressiveness relative to the transformer, we overcome this gap through training strategies that leverage the autoregressive structure of the model—namely, variational neural annealing. Our findings support the RetNet as a means of improving the time complexity of NQS without sacrificing accuracy. We provide further evidence that the ablative improvements of neural annealing extend beyond the RetNet architecture, suggesting it would serve as an effective general training strategy for autoregressive NQS.