An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code

Restricted Boltzmann machines (RBMs) have demonstrated considerable success as variational quantum states; however, their representational power remains incompletely understood. In this work, we present an analytical proof that RBMs can exactly and efficiently represent stabilizer code states—a clas...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuan-Hang Zhang, Zhian Jia, Yu-Chun Wu, Guang-Can Guo
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/27/6/627
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167953692033024
author Yuan-Hang Zhang
Zhian Jia
Yu-Chun Wu
Guang-Can Guo
author_facet Yuan-Hang Zhang
Zhian Jia
Yu-Chun Wu
Guang-Can Guo
author_sort Yuan-Hang Zhang
collection DOAJ
description Restricted Boltzmann machines (RBMs) have demonstrated considerable success as variational quantum states; however, their representational power remains incompletely understood. In this work, we present an analytical proof that RBMs can exactly and efficiently represent stabilizer code states—a class of highly entangled quantum states that are central to quantum error correction. Given a set of stabilizer generators, we develop an efficient algorithm to determine both the RBM architecture and the exact values of its parameters. Our findings provide new insights into the expressive power of RBMs, highlighting their capability to encode highly entangled states, and may serve as a useful tool for the classical simulation of quantum error-correcting codes.
format Article
id doaj-art-4a54fdadb5a044ae890f0593abb44a74
institution OA Journals
issn 1099-4300
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-4a54fdadb5a044ae890f0593abb44a742025-08-20T02:21:06ZengMDPI AGEntropy1099-43002025-06-0127662710.3390/e27060627An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer CodeYuan-Hang Zhang0Zhian Jia1Yu-Chun Wu2Guang-Can Guo3Department of Physics, University of California, San Diego, CA 92093, USACentre for Quantum Technologies, National University of Singapore, Singapore 117543, SingaporeCAS Key Laboratory of Quantum Information, School of Physics, University of Science and Technology of China, Hefei 230026, ChinaCAS Key Laboratory of Quantum Information, School of Physics, University of Science and Technology of China, Hefei 230026, ChinaRestricted Boltzmann machines (RBMs) have demonstrated considerable success as variational quantum states; however, their representational power remains incompletely understood. In this work, we present an analytical proof that RBMs can exactly and efficiently represent stabilizer code states—a class of highly entangled quantum states that are central to quantum error correction. Given a set of stabilizer generators, we develop an efficient algorithm to determine both the RBM architecture and the exact values of its parameters. Our findings provide new insights into the expressive power of RBMs, highlighting their capability to encode highly entangled states, and may serve as a useful tool for the classical simulation of quantum error-correcting codes.https://www.mdpi.com/1099-4300/27/6/627neural network quantum statequantum stabilizer coderestricted Boltzmann machine
spellingShingle Yuan-Hang Zhang
Zhian Jia
Yu-Chun Wu
Guang-Can Guo
An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
Entropy
neural network quantum state
quantum stabilizer code
restricted Boltzmann machine
title An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
title_full An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
title_fullStr An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
title_full_unstemmed An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
title_short An Efficient Algorithmic Way to Construct Boltzmann Machine Representations for Arbitrary Stabilizer Code
title_sort efficient algorithmic way to construct boltzmann machine representations for arbitrary stabilizer code
topic neural network quantum state
quantum stabilizer code
restricted Boltzmann machine
url https://www.mdpi.com/1099-4300/27/6/627
work_keys_str_mv AT yuanhangzhang anefficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode
AT zhianjia anefficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode
AT yuchunwu anefficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode
AT guangcanguo anefficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode
AT yuanhangzhang efficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode
AT zhianjia efficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode
AT yuchunwu efficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode
AT guangcanguo efficientalgorithmicwaytoconstructboltzmannmachinerepresentationsforarbitrarystabilizercode