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

Nature Physics

Restricted Boltzmann machines in quantum physics

Roger G. Melko, Giuseppe Carleo, Juan Carrasquilla, J. I. Cirac

Published Jun 24, 2019• 216 citations
Publisher
DOI
10.1038/s41567-019-0545-1

Related papers

Modeling Many-Body Physics with Restricted Boltzmann Machines

Roger G. Melko

Bulletin of the American Physical Society•Mar 5, 2018•0 citations

Quantum Discriminative Restricted Boltzmann Machine

Kouki Yonaga, Masayuki Ohzeki

Journal of the Physical Society of Japan•Apr 24, 2025•2 citations

A hybrid quantum-classical approach for inference on restricted Boltzmann machines

Mārtiņš Kālis, Andris Locāns, Rolands Šikovs +2 more

arXiv:2304.12418•Quantum Machine Intelligence•Nov 21, 2023•12 citations

Multi-Layer Restricted Boltzmann Machine Representation of 1D Quantum Many-Body Wave Functions

Huan He, Yunqin Zheng, Bogdan Andrei Bernevig +1 more

We consider representing two classes of 1D quantum wave functions of spin systems, including the AKLT and CFT correlator wave functions, in terms of multi-layer restricted Boltzmann machines. In our prescription, the AKLT wave function can be exactly represented by a 2-layer restricted Boltzmann machine with five hidden spins per visible spin. The construction can be generalized to prove that any MPS wave function on $N$ unit cells with finite bond dimension can be approximated by a 2-layer restricted Boltzmann machine with $\mathcal{O}(N)$ hidden spins within an error which scales linearly with $N$. The Haldane-Shastry wave function or a chiral boson CFT correlator wave function, as any Jastrow type of wave functions, can be exactly written as a 1-layer Boltzmann machine with $\mathcal{O}(N^2)$ hidden spins and $N$ visible spins. Applying the cumulant expansion, we further find that the chiral boson CFT correlator wave function (with small vertex operator conformal dimension $α$, i.e., $α<0.1$) can be approximated, within 99.9\% accuracy up to 22 visible spins, by a 1-layer RBM with $\mathcal{O}(N)$ hidden spins. The cumulant expansion also leads us to a physically inspiring result in which the hidden spins of the restricted Boltzmann machine can be interpreted as the conformal tower of the chiral boson CFT on the cylinder.

arXiv:1910.13454•Oct 29, 2019•10 citations

Restricted Boltzmann machines in physics: concepts, theories and applications

Kai Zhang, Sora Sakai

Abstract A restricted Boltzmann machine (RBM) is a two-layer neural-network machine-learning model comprising a visible layer that represents observed data and a hidden layer that captures correlations among the visible units. Rooted in ideas from statistical mechanics, RBMs provide a probabilistic framework for modeling complex, high-dimensional distributions through an energy function and a corresponding Boltzmann distribution. This review offers an accessible introduction to RBMs from a physics-oriented perspective, focusing on their core concepts and training principles. We survey key theoretical developments that interpret RBMs as many-body systems, highlighting their equilibrium/non-equilibrium thermodynamics, learning dynamics, mean-field properties, phase diagrams, and free energy calculation. We further discuss recent applications of RBMs to a range of physics problems, including quantum-mechanical wavefunction representation, statistical-mechanical Boltzmann distribution modeling, and biological protein sequence analysis.

Journal of Physics Communications•Sep 1, 2026•0 citations

Quantum Boltzmann Machine

Bohdan Kulchytskyy, Evgeny Andriyash, Mohammed Amin +1 more

Bulletin of the American Physical Society•Mar 18, 2016•28 citations
We consider representing two classes of 1D quantum wave functions of spin systems, including the AKLT and CFT correlator wave functions, in terms of multi-layer restricted Boltzmann machines. In our prescription, the AKLT wave function can be exactly represented by a 2-layer restricted Boltzmann machine with five hidden spins per visible spin. The construction can be generalized to prove that any MPS wave function on NNN unit cells with finite bond dimension can be approximated by a 2-layer restricted Boltzmann machine with O(N)\mathcal{O}(N)O(N) hidden spins within an error which scales linearly with NNN. The Haldane-Shastry wave function or a chiral boson CFT correlator wave function, as any Jastrow type of wave functions, can be exactly written as a 1-layer Boltzmann machine with O(N2)\mathcal{O}(N^2)O(N2) hidden spins and NNN visible spins. Applying the cumulant expansion, we further find that the chiral boson CFT correlator wave function (with small vertex operator conformal dimension ααα, i.e., α<0.1α<0.1α<0.1) can be approximated, within 99.9\% accuracy up to 22 visible spins, by a 1-layer RBM with O(N)\mathcal{O}(N)O(N) hidden spins. The cumulant expansion also leads us to a physically inspiring result in which the hidden spins of the restricted Boltzmann machine can be interpreted as the conformal tower of the chiral boson CFT on the cylinder.
Abstract A restricted Boltzmann machine (RBM) is a two-layer neural-network machine-learning model comprising a visible layer that represents observed data and a hidden layer that captures correlations among the visible units. Rooted in ideas from statistical mechanics, RBMs provide a probabilistic framework for modeling complex, high-dimensional distributions through an energy function and a corresponding Boltzmann distribution. This review offers an accessible introduction to RBMs from a physics-oriented perspective, focusing on their core concepts and training principles. We survey key theoretical developments that interpret RBMs as many-body systems, highlighting their equilibrium/non-equilibrium thermodynamics, learning dynamics, mean-field properties, phase diagrams, and free energy calculation. We further discuss recent applications of RBMs to a range of physics problems, including quantum-mechanical wavefunction representation, statistical-mechanical Boltzmann distribution modeling, and biological protein sequence analysis.