Towards quantum machine learning with tensor networks

Huggins, William; Patil, Piyush; Mitchell, Bradley; Whaley, K. Birgitta; Stoudenmire, E. Miles

doi:10.1088/2058-9565/aaea94

Title: Towards quantum machine learning with tensor networks

Journal Article · Wed Jan 09 00:00:00 EST 2019 · Quantum Science and Technology

DOI:https://doi.org/10.1088/2058-9565/aaea94· OSTI ID:1604671

^[1]; Patil, Piyush ^[1]; Mitchell, Bradley ^[1];

^[1]; Stoudenmire, E. Miles ^[2]

Univ. of California, Berkeley, CA (United States)
Flatiron Inst., New York, NY (United States)

Machine learning is a promising application of quantum computing, but challenges remain for implementation today because near-term devices have a limited number of physical qubits and high error rates. Motivated by the usefulness of tensor networks for machine learning in the classical context, we propose quantum computing approaches to both discriminative and generative learning, with circuits based on tree and matrix product state tensor networks, that could already have benefits with such near-term devices. The result is a unified framework in which classical and quantum computing can benefit from the same theoretical and algorithmic developments, and the same model can be trained classically then transferred to the quantum setting for additional optimization. Tensor network circuits can also provide qubit-efficient schemes in which, depending on the architecture, the number of physical qubits required scales only logarithmically with, or independently of the input or output data sizes. Here, we demonstrate our proposals with numerical experiments, training a discriminative model to perform handwriting recognition using a hybrid quantum-classical optimization procedure that could be carried out on quantum hardware today, and testing the noise resilience of the trained model.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); National Institutes of Health (NIH)

Grant/Contract Number:: AC02-05CH11231; S1OD023532

OSTI ID:: 1604671

Journal Information:: Quantum Science and Technology, Vol. 4, Issue 2; ISSN 2058-9565

Publisher:: IOPscienceCopyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 104 works

Citation information provided by
Web of Science

References (33)

Density-matrix renormalization study of the Hubbard model [4]on a Bethe lattice Lepetit, M. -B.; Cousy, M.; Pastor, G. M. The European Physical Journal B, Vol. 13, Issue 3 https://doi.org/10.1007/s100510050053	journal	January 2000
The density-matrix renormalization group in the age of matrix product states Schollwöck, Ulrich Annals of Physics, Vol. 326, Issue 1 https://doi.org/10.1016/j.aop.2010.09.012	journal	January 2011
Implementation of the simultaneous perturbation algorithm for stochastic optimization Spall, J. C. IEEE Transactions on Aerospace and Electronic Systems, Vol. 34, Issue 3 https://doi.org/10.1109/7.705889	journal	July 1998
Learning relevant features of data with multi-scale tensor networks Stoudenmire, E. Miles Quantum Science and Technology, Vol. 3, Issue 3 https://doi.org/10.1088/2058-9565/aaba1a	journal	April 2018
Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines Cheng, Song; Chen, Jing; Wang, Lei Entropy, Vol. 20, Issue 8 https://doi.org/10.3390/e20080583	journal	August 2018
Characterizing quantum supremacy in near-term devices Boixo, Sergio; Isakov, Sergei V.; Smelyanskiy, Vadim N. Nature Physics, Vol. 14, Issue 6 https://doi.org/10.1038/s41567-018-0124-x	journal	April 2018
Class of Quantum Many-Body States That Can Be Efficiently Simulated Vidal, G. Physical Review Letters, Vol. 101, Issue 11 https://doi.org/10.1103/PhysRevLett.101.110501	journal	September 2008
Demonstration of a quantum error detection code using a square lattice of four superconducting qubits Córcoles, A. D.; Magesan, Easwar; Srinivasan, Srikanth J. Nature Communications, Vol. 6, Issue 1 https://doi.org/10.1038/ncomms7979	journal	April 2015
Unsupervised Generative Modeling Using Matrix Product States Han, Zhao-Yu; Wang, Jun; Fan, Heng Physical Review X, Vol. 8, Issue 3 https://doi.org/10.1103/PhysRevX.8.031012	journal	July 2018
No Signaling and Quantum Key Distribution Barrett, Jonathan; Hardy, Lucien; Kent, Adrian Physical Review Letters, Vol. 95, Issue 1 https://doi.org/10.1103/PhysRevLett.95.010503	journal	June 2005
Tensor Network States and Geometry Evenbly, G.; Vidal, G. Journal of Statistical Physics, Vol. 145, Issue 4 https://doi.org/10.1007/s10955-011-0237-4	journal	June 2011
The theory of variational hybrid quantum-classical algorithms McClean, Jarrod R.; Romero, Jonathan; Babbush, Ryan New Journal of Physics, Vol. 18, Issue 2 https://doi.org/10.1088/1367-2630/18/2/023023	journal	February 2016
A variational eigenvalue solver on a photonic quantum processor Peruzzo, Alberto; McClean, Jarrod; Shadbolt, Peter Nature Communications, Vol. 5, Issue 1 https://doi.org/10.1038/ncomms5213	journal	July 2014
A practical introduction to tensor networks: Matrix product states and projected entangled pair states Orús, Román Annals of Physics, Vol. 349 https://doi.org/10.1016/j.aop.2014.06.013	journal	October 2014
A New Scheme for the Tensor Representation Hackbusch, W.; Kühn, S. Journal of Fourier Analysis and Applications, Vol. 15, Issue 5 https://doi.org/10.1007/s00041-009-9094-9	journal	October 2009
Simulation of two-dimensional quantum systems using a tree tensor network that exploits the entropic area law Tagliacozzo, L.; Evenbly, G.; Vidal, G. Physical Review B, Vol. 80, Issue 23 https://doi.org/10.1103/PhysRevB.80.235127	journal	December 2009
Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer Shor, Peter W. SIAM Journal on Computing, Vol. 26, Issue 5 https://doi.org/10.1137/S0097539795293172	journal	October 1997
Gradient-based learning applied to document recognition Lecun, Y.; Bottou, L.; Bengio, Y. Proceedings of the IEEE, Vol. 86, Issue 11 https://doi.org/10.1109/5.726791	journal	January 1998
Preparing Projected Entangled Pair States on a Quantum Computer Schwarz, Martin; Temme, Kristan; Verstraete, Frank Physical Review Letters, Vol. 108, Issue 11 https://doi.org/10.1103/PhysRevLett.108.110502	journal	March 2012
Thermodynamic Limit of Density Matrix Renormalization Östlund, Stellan; Rommer, Stefan Physical Review Letters, Vol. 75, Issue 19 https://doi.org/10.1103/PhysRevLett.75.3537	journal	November 1995
Matrix product states, projected entangled pair states, and variational renormalization group methods for quantum spin systems Verstraete, F.; Murg, V.; Cirac, J. I. Advances in Physics, Vol. 57, Issue 2 https://doi.org/10.1080/14789940801912366	journal	March 2008
Efficient Classical Simulation of Slightly Entangled Quantum Computations Vidal, Guifré Physical Review Letters, Vol. 91, Issue 14 https://doi.org/10.1103/PhysRevLett.91.147902	journal	October 2003
Preparing topological projected entangled pair states on a quantum computer Schwarz, Martin; Temme, Kristan; Verstraete, Frank Physical Review A, Vol. 88, Issue 3 https://doi.org/10.1103/PhysRevA.88.032321	journal	September 2013
Simulation of two-dimensional quantum systems using a tree tensor network that exploits the entropic area law Tagliacozzo, L.; Evenbly, G.; Vidal, G. arXiv https://doi.org/10.48550/arxiv.0903.5017	text	January 2009
The density-matrix renormalization group in the age of matrix product states Schollwoeck, Ulrich arXiv https://doi.org/10.48550/arxiv.1008.3477	text	January 2010
Preparing projected entangled pair states on a quantum computer Schwarz, Martin; Temme, Kristan; Verstraete, Frank arXiv https://doi.org/10.48550/arxiv.1104.1410	text	January 2011
Tensor network states and geometry Evenbly, G.; Vidal, G. arXiv https://doi.org/10.48550/arxiv.1106.1082	text	January 2011
Characterizing Quantum Supremacy in Near-Term Devices Boixo, Sergio; Isakov, Sergei V.; Smelyanskiy, Vadim N. arXiv https://doi.org/10.48550/arxiv.1608.00263	text	January 2016
Unsupervised Generative Modeling Using Matrix Product States Han, Zhao-Yu; Wang, Jun; Fan, Heng arXiv https://doi.org/10.48550/arxiv.1709.01662	text	January 2017
Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines Cheng, Song; Chen, Jing; Wang, Lei arXiv https://doi.org/10.48550/arxiv.1712.04144	text	January 2017
Efficient classical simulation of slightly entangled quantum computations Vidal, Guifre arXiv https://doi.org/10.48550/arxiv.quant-ph/0301063	text	January 2003
Finitely correlated states on quantum spin chains Fannes, M.; Nachtergaele, B.; Werner, R. F. Communications in Mathematical Physics, Vol. 144, Issue 3 https://doi.org/10.1007/bf02099178	journal	March 1992
A fast quantum mechanical algorithm for database search Grover, Lov K. arXiv https://doi.org/10.48550/arxiv.quant-ph/9605043	preprint	January 1996

Cited By (11)

Tensor-Based Algorithms for Image Classification Klus, Stefan; Gelß, Patrick Algorithms, Vol. 12, Issue 11 https://doi.org/10.3390/a12110240	journal	November 2019
Parameterized quantum circuits as machine learning models Benedetti, Marcello; Lloyd, Erika; Sack, Stefan Quantum Science and Technology, Vol. 4, Issue 4 https://doi.org/10.1088/2058-9565/ab4eb5	journal	October 2019
Quantum convolutional neural networks Cong, Iris; Choi, Soonwon; Lukin, Mikhail D. Nature Physics, Vol. 15, Issue 12 https://doi.org/10.1038/s41567-019-0648-8	journal	August 2019
Learning and inference on generative adversarial quantum circuits Zeng, Jinfeng; Wu, Yufeng; Liu, Jin-Guo Physical Review A, Vol. 99, Issue 5 https://doi.org/10.1103/physreva.99.052306	journal	May 2019
Matrix Product State–Based Quantum Classifier Bhatia, Amandeep Singh; Saggi, Mandeep Kaur; Kumar, Ajay Neural Computation, Vol. 31, Issue 7 https://doi.org/10.1162/neco_a_01202	journal	July 2019
Variational quantum eigensolver with fewer qubits Liu, Jin-Guo; Zhang, Yi-Hong; Wan, Yuan Physical Review Research, Vol. 1, Issue 2 https://doi.org/10.1103/physrevresearch.1.023025	journal	September 2019
Generative tensor network classification model for supervised machine learning Sun, Zheng-Zhi; Peng, Cheng; Liu, Ding Physical Review B, Vol. 101, Issue 7 https://doi.org/10.1103/physrevb.101.075135	journal	February 2020
Hierarchical quantum classifiers Grant, Edward; Benedetti, Marcello; Cao, Shuxiang npj Quantum Information, Vol. 4, Issue 1 https://doi.org/10.1038/s41534-018-0116-9	journal	December 2018
Learning and Inference on Generative Adversarial Quantum Circuits Zeng, Jinfeng; Wu, Yufeng; Liu, Jin-Guo arXiv https://doi.org/10.48550/arxiv.1808.03425	text	January 2018
Variational Quantum Eigensolver with Fewer Qubits Liu, Jin-Guo; Zhang, Yi-Hong; Wan, Yuan arXiv https://doi.org/10.48550/arxiv.1902.02663	text	January 2019
Parameterized quantum circuits as machine learning models Benedetti, Marcello; Lloyd, Erika; Sack, Stefan arXiv https://doi.org/10.48550/arxiv.1906.07682	text	January 2019

Similar Records

Hybrid Quantum-Classical Neural Networks

Conference · Tue Nov 01 00:00:00 EDT 2022 · OSTI ID:1604671

Arthur, Davis; Date, Prasanna

Distributed Quantum Learning with co-Management in a Multi-tenant Quantum System

Conference · Fri Dec 15 00:00:00 EST 2023 · OSTI ID:1604671

D'Onofrio, Anthony; Hossain, Amir; Santana, Lesther; +5 more

ExaTN: Scalable GPU-Accelerated High-Performance Processing of General Tensor Networks at Exascale

Journal Article · Wed Jul 06 00:00:00 EDT 2022 · Frontiers in Applied Mathematics and Statistics · OSTI ID:1604671

Lyakh, Dmitry I.; Nguyen, Thien; Claudino, Daniel; +2 more

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS

Title: Towards quantum machine learning with tensor networks

Citation Formats

References (33)

Cited By (11)

Similar Records

Related Subjects