Variational neural annealing
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Many important challenges in science and technology can be cast as optimization problems. When viewed in a statistical physics framework, these can be tackled by simulated annealing, where a gradual cooling procedure helps search for ground-state solutions of a target Hamiltonian. Although powerful, simulated annealing is known to have prohibitively slow sampling dynamics when the optimization landscape is rough or glassy. Here we show that, by generalizing the target distribution with a parameterized model, an analogous annealing framework based on the variational principle can be used to search for ground-state solutions. Modern autoregressive models such as recurrent neural networks provide ideal parameterizations because they can be sampled exactly without slow dynamics, even when the model encodes a rough landscape. We implement this procedure in the classical and quantum settings on several prototypical spin glass Hamiltonians and find that, on average, it substantially outperforms traditional simulated annealing in the asymptotic limit, illustrating the potential power of this yet unexplored route to optimization. Optimization problems can be described in terms of a statistical physics framework. This offers the possibility to make use of ‘simulated annealing’, which is a procedure to search for a target solution similar to the gradual cooling of a condensed matter system to its ground state. The approach can now be sped up significantly by implementing a model of recurrent neural networks, in a new strategy called variational neural annealing.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542
Spin Glass Theory and Beyond: An Introduction to the Replica Method and Its Applications
Mezard, M., Parisi, G., & Virasoro, M. (1986) · World Scientific Lecture Notes in Physics · doi:10.1142/0271 · Cited by 3,653
Ising formulations of many NP problems
Lucas, A. (2014) · Frontiers in Physics · doi:10.3389/fphy.2014.00005 · Cited by 2,512
Quantum annealing in the transverse Ising model
Kadowaki, T., & Nishimori, H. (1998) · Physical Review E · doi:10.1103/physreve.58.5355 · Cited by 2,339 · cited 2×
“We note that periodic boundary conditions σP + 1 ≡ σ1 arise because of the trace in equation (25).”
BackgroundMethodEvidence for quantum annealing with more than one hundred qubits
Boixo, S., Rønnow, T. F., Isakov, S. V., Wang, Z., Wecker, D., Lidar, D. A., Martinis, J. M., & Troyer, M. (2014) · Nature Physics · doi:10.1038/nphys2900 · Cited by 810
Quantum Annealing of a Disordered Magnet
Brooke, J., Bitko, D., F., T., Rosenbaum, & Aeppli, G. (1999) · Science · doi:10.1126/science.284.5415.779 · Cited by 518
Recurrent neural network wave functions
Hibat-Allah, M., Ganahl, M., Hayward, L. E., Melko, R. G., & Carrasquilla, J. (2020) · Physical Review Research · doi:10.1103/physrevresearch.2.023358 · Cited by 274
Self-citationMachine learning for combinatorial optimization: A methodological tour d'horizon
Bengio, Y., Lodi, A., & Prouvost, A. (2021) · European Journal of Operational Research · doi:10.1016/j.ejor.2020.07.063 · Cited by 195
Cited by
Classical variational simulation of the Quantum Approximate Optimization Algorithm
Medvidović, M., & Carleo, G. (2021) · npj Quantum Information · doi:10.1038/s41534-021-00440-z · Cited by 79
Variational benchmarks for quantum many-body problems
Wu, D., Rossi, R., Vicentini, F., Astrakhantsev, N., Becca, F., Cao, X., Carrasquilla, J., Ferrari, F., Georges, A., Hibat-Allah, M., et al. (2024) · Science · doi:10.1126/science.adg9774 · Cited by 79
“In a similar fashion to tensor networks, tensorized versions of RNNs have been used to provide higher expressive power [117–119] and more accurate estimations of ground-state energies that outperform DMRG in certain regimes [118, 119].”
MethodSelf-citationInvestigating topological order using recurrent neural networks
Hibat-Allah, M., Melko, R. G., & Carrasquilla, J. (2023) · Physical Review B · doi:10.1103/physrevb.108.075152 · Cited by 27
Self-citationNeural network approach to quasiparticle dispersions in doped antiferromagnets
Lange, H., Döschl, F., Carrasquilla, J., & Bohrdt, A. (2024) · Communications Physics · doi:10.1038/s42005-024-01678-7 · Cited by 18
Self-citation(2023) · doi:10.1038/s42005-023-01416-5 · Cited by 10
Metadata
- Authors
- Hibat-Allah, M., Inack, E. M., Wiersema, R., Melko, R. G., & Carrasquilla, J.
- Venue
- Nature Machine Intelligence
- Published
- 2021-10-25
- Volume
- 3
- Issue
- 11
- Pages
- 952-961
- ISSN
- 2522-5839 (ISSN-L)
- OpenAlex
- W3122174941
- Cited by
- 78
- References
- 8
- FWCI
- 3.97
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Variational neural annealing. https://app.cochat.ai/papers/10.1038/s42256-021-00401-3
- The paper
- Hibat-Allah, M., Inack, E. M., Wiersema, R., Melko, R. G., & Carrasquilla, J. (2021). Variational neural annealing. Nature Machine Intelligence. https://doi.org/10.1038/s42256-021-00401-3
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.