- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Provable learning of quantum states with graphical models

Liming Zhao1,*, Naixu Guo2,†, Ming-Xing Luo1, and Patrick Rebentrost2,‡

  • *Contact author: 100xiaoai@163.com
  • †Contact author: naixug@u.nus.edu
  • ‡Contact author: cqtfpr@nus.edu.sg
PDF

Phys. Rev. Research 8, 013109 – Published 30 January, 2026

DOI: https://doi.org/10.1103/1355-xvpx

Abstract

The complete learning of any unknown many-body systems requires a number of samples exponentially in the particle number. Several works consider subclasses of physical meaningful states such as stabilizer states or high-temperature Gibbs states that can be learned in polynomial sample complexity. Others consider to learn states under special assumptions, such as PAC learning and shadow tomography. In this work, we consider learning many-body systems that can be approximately represented by restricted Boltzmann machines (RBMs). We exhibit robustness results for efficient provable two-hop neighborhood learning method for ferromagnetic and locally consistent RBMs. We consider the Lp norm as a distance measure, including both total variation distance and max-norm distance in the limit. We show that various quantum states can be learned with a sample complexity exponentially better than the naive state tomography. Our results establish a broader theoretical framework for the efficient learning of complex quantum many-body systems.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (59)

  1. G. M. D’Ariano, M. G. A. Paris, and M. F. Sacchi, Quantum tomography, Adv. Imaging Electron Phys., 128, 205 (2003).
  2. J. Wright, How to learn a quantum state, Ph.D. thesis, Carnegie Mellon University, 2016.
  3. M. Mohseni, A. T. Rezakhani, and D. A. Lidar, Quantum-process tomography: Resource analysis of different strategies, Phys. Rev. A 77, 032322 (2008).
  4. I. L. Chuang and M. A. Nielsen, Prescription for experimental determination of the dynamics of a quantum black box, J. Mod. Opt. 44, 2455 (1997).
  5. S. T. Flammia, D. Gross, Y.-K. Liu, and J. Eisert, Quantum tomography via compressed sensing: Error bounds, sample complexity and efficient estimators, New J. Phys. 14, 095022 (2012).
  6. R. O’Donnell, and J. Wright, Efficient quantum tomography, in Proceedings of the Forty-Eighth Annual A CM Symposium on Theory of Computing, STOC’16 (Association for Computing Machinery, New York, NY, 2016), pp. 899–912.
  7. J. Haah, A. W. Harrow, Z. Ji, X. Wu, and N. Yu, Sample-optimal tomography of quantum states, in Proceedings of the Forty-Eighth Annual ACM Symposium on Theory of Computing, STOC’16 (Association for Computing Machinery, New York, NY, 2016), pp. 913–925.
  8. J. B. Altepeter, D. Branning, E. Jeffrey, T. C. Wei, P. G. Kwiat, R. T. Thew, J. L. O’Brien, M. A. Nielsen, and A. G. White, Ancilla-assisted quantum process tomography, Phys. Rev. Lett. 90, 193601 (2003).
  9. A. Anshu and S. Arunachalam, A survey on the complexity of learning quantum states, Nat. Rev. Phys. 6, 59 (2024).
  10. E. Bairey, I. Arad, and N. H. Lindner, Learning a local Hamiltonian from local measurements, Phys. Rev. Lett. 122, 020504 (2019).
  11. N. Wiebe, C. Granade, C. Ferrie, and D. G. Cory, Hamiltonian learning and certification using quantum resources, Phys. Rev. Lett. 112, 190501 (2014).
  12. J. Wang, S. Paesani, R. Santagati, S. Knauer, A. A. Gentile, N. Wiebe, M. Petruzzella, J. L. O’Brien, J. G. Rarity, A. Laing, and M. G. Thompson, Experimental quantum Hamiltonian learning, Nat. Phys. 13, 551 (2017).
  13. T. J. Evans, R. Harper, and S. T. Flammia, Scalable Bayesian Hamiltonian learning, arXiv:1912.07636.
  14. A. Anshu, S. Arunachalam, T. Kuwahara, and M. Soleimanifar, Sample-efficient learning of interacting quantum systems, Nat. Phys. 17, 931 (2021).
  15. A. Montanaro, Learning stabilizer states by bell sampling, arXiv:1707.04012.
  16. S. Aaronson, Shadow tomography of quantum states, SIAM J. Comput. 49, STOC18-368 (2020).
  17. H.-Y. Huang, S. T. Flammia, and J. Preskill, Foundations for learning from noisy quantum experiments, arXiv:2204.13691.
  18. H.-Y. Huang, R. Kueng, and J. Preskill, Predicting many properties of a quantum system from very few measurements, Nat. Phys. 16, 1050 (2020).
  19. H.-Y. Huang, R. Kueng, G. Torlai, V. V. Albert, and J. Preskill, Provably efficient machine learning for quantum many-body problems, Science 377, 6613 (2022).
  20. C. Bertoni, J. Haferkamp, M. Hinsche, M. Ioannou, J. Eisert, and H. Pashayan, Shallow shadows: Expectation estimation using low-depth random clifford circuits, Phys. Rev. Lett. 133, 020602 (2024).
  21. K. I. Aoki, and T. Kobayashi, Restricted Boltzmann machines for the long range ising models, Mod. Phys. Lett. B 30, 1650401 (2016).
  22. K. Ch’ng, J. Carrasquilla, R. G. Melko, and E. Khatami, Machine learning phases of strongly correlated fermions, Phys. Rev. X 7, 031038 (2017).
  23. P. Broecker, J. Carrasquilla, R. G. Melko, and S. Trebst, Machine learning quantum phases of matter beyond the fermion sign problem, Sci. Rep. 7, 8823 (2017).
  24. J. Carrasquilla and R. G. Melko, Machine learning phases of matter, Nat. Phys. 13, 431 (2017).
  25. G. Carleo, I. Cirac, K. Cranmer, L. Daudet, M. Schuld, N. Tishby, L. Vogt-Maranto, and L. Zdeborová, Machine learning and the physical sciences, Rev. Mod. Phys. 91, 045002 (2019).
  26. N. L. Roux, and Y. Bengio, Representational power of restricted Boltzmann machines and deep belief networks, Neural Comput. 20, 1631 (2008).
  27. G. Carleo and M. Troyer, Solving the quantum many-body problem with artificial neural networks, Science 355, 602 (2017).
  28. D.-L. Deng, X. Li, and S. D. Sarma, Machine learning topological states, Phys. Rev. B 96, 195145 (2017).
  29. Y. Huang and J. E. Moore, Neural network representation of tensor network and chiral states, Phys. Rev. Lett. 127, 170601 (2021).
  30. J. Carrasquilla, G. Torlai, R. G. Melko, and L. Aolita, Reconstructing quantum states with generative models, Nat. Mach. Intell. 1, 155 (2019).
  31. G. Torlai, G. Mazzola, J. Carrasquilla, M. Troyer, R. Melko, and G. Carleo, Neural-network quantum state tomography, Nat. Phys. 14, 447 (2018).
  32. M. Neugebauer, L. Fischer, A. Jäger, S. Czischek, S. Jochim, M. Weidemüller, and M. Gärttner, Neural-network quantum state tomography in a two-qubit experiment, Phys. Rev. A 102, 042604 (2020).
  33. D.-L. Deng, X. Li, and S. D. Sarma, Quantum entanglement in neural network states, Phys. Rev. X 7, 021021 (2017)b.
  34. Y. Levine, O. Sharir, N. Cohen, and A. Shashua, Quantum entanglement in deep learning architectures, Phys. Rev. Lett. 122, 065301 (2019).
  35. C. Harney, S. Pirandola, A. Ferraro, and M. Paternostro, Entanglement classification via neural network quantum states, New J. Phys. 22, 045001 (2020).
  36. P. M. Long and R. A. Servedio, Restricted Boltzmann machines are hard to approximately evaluate or simulate, in Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML’10 (Omnipress, Madison, WI, 2010), pp. 703–710.
  37. N. P. Santhanam, and M. J. Wainwright, Information-theoretic limits of selecting binary graphical models in high dimensions, IEEE Trans. Inf. Theory 58, 4117 (2012).
  38. G. Bresler, F. Koehler, and A. Moitra, Learning restricted Boltzmann machines via influence maximization, in Proceedings of the 51st Annual A CM SIGACT Symposium on Theory of Computing, STOC (Association for Computing Machinery, New York, NY, 2019), pp. 828–839.
  39. S. Goel, Learning restricted Boltzmann machines with arbitrary external fields, arXiv:1906.06595.
  40. S. Goel and A. R Klivans, Learning neural networks with two nonlinear layers in polynomial time, in Conference on Learning Theory (PMLR, Phoenix, AZ, USA, 2019), pp. 1470–1499.
  41. R. Salakhutdinov, A. Mnih, and G. Hinton, Restricted Boltzmann machines for collaborative filtering, in Proceedings of the 24th International Conference on Machine Learning (Omnipress, Corvallis, Oregon, USA, 2007), pp. 791–798.
  42. H. Larochelle and Y. Bengio, Classification using discriminative restricted Boltzmann machines, in Proceedings of the 25th International Conference on Machine Learning (ACM, Helsinki, Finland, 2008), pp. 536–543.
  43. G. Bresler, Efficiently learning Ising models on arbitrary graphs, in Proceedings of the Forty-Seventh Annual ACM Symposium on Theory of Computing (ACM, Portland, OR, USA, 2015), pp. 771–782.
  44. Z.-A. Jia, L. Wei, Y.-C. Wu, Guang-Can Guo, and Guo-Ping Guo, Entanglement area law for shallow and deep quantum neural network states, New J. Phys. 22, 053022 (2020).
  45. S. Sugiura and A. Shimizu, Thermal pure quantum states at finite temperature, Phys. Rev. Lett. 108, 240401 (2012).
  46. S. Sugiura and A. Shimizu, Canonical thermal pure quantum state, Phys. Rev. Lett. 111, 010401 (2013).
  47. S. Aaronson, The learnability of quantum states, Proc. R. Soc. A 463, 3089 (2007).
  48. S. Aaronson, Shadow tomography of quantum states, in Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing (ACM, New York, USA, 2018), pp. 325–338.
  49. C. Bădescu and R. O’ Donnell, Improved quantum data analysis, in Proceedings of the 53rd Annual A CM SIGACT Symposium on Theory of Computing (ACM Press, New York, USA, 2021), pp. 1398–1411.
  50. M. Cramer, M. B. Plenio, S. T. Flammia, R. Somma, D. Gross, S. D. Bartlett, O. Landon-Cardinal, D. Poulin, and Y.-K. Liu, Efficient quantum state tomography, Nat. Commun. 1, 149 (2010).
  51. T. Baumgratz, D. Gross, M. Cramer, and M. B. Plenio, Scalable reconstruction of density matrices, Phys. Rev. Lett. 111, 020401 (2013).
  52. T. Baumgratz, A. Nüßeler, M. Cramer, and M. B. Plenio, A scalable maximum likelihood method for quantum state tomography, New J. Phys. 15, 125004 (2013).
  53. M. Holzäpfel, T. Baumgratz, M. Cramer, and M. B. Plenio, Scalable reconstruction of unitary processes and Hamiltonians, Phys. Rev. A 91, 042129 (2015).
  54. B. P. Lanyon, C. Maier, M. Holzäpfel, T. Baumgratz, C. Hempel, P. Jurcevic, I. Dhand, A. S. Buyskikh, A. J. Daley, M. Cramer, M. B. Plenio, R. Blatt, and C. F. Roos, Efficient tomography of a quantum many-body system, Nat. Phys. 13, 1158 (2017).
  55. J. Martens, A. Chattopadhya, T. Pitassi, and R. Zemel, On the representational efficiency of restricted Boltzmann machines, in Advances in Neural Information Processing Systems, edited by C. J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger (Curran Associates, Inc., Red Hook, New York, USA, 2013), Vol. 26.
  56. X. Gao and L.-M. Duan, Efficient representation of quantum many-body states with deep neural networks, Nat. Commun. 8, 662 (2017).
  57. G. E. Hinton and R. R. Salakhutdinov, Reducing the dimensionality of data with neural networks, Science 313, 504 (2006).
  58. A. Coates, A. Ng, and H. Lee, An analysis of single-layer networks in unsupervised feature learning, in Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, edited by G. Gordon, D. Dunson, and M. Dudík, Proceedings of Machine Learning Research (PMLR, Fort Lauderdale, FL, 2011), Vol. 15, pp. 215–223.
  59. A. Klivans and R. Meka, Learning graphical models using multiplicative weights, in 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS) (IEEE, Piscataway, NJ, USA, 2017), pp. 343–354.

Outline

Information

Phys. Rev. Research 8, 013109– Published 30 January, 2026
  • Received 4 March 2025
  • Accepted 8 December 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation