- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Letters

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

Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric

Tobias Haug1,2,* and M. S. Kim2

  • *Contact author: tobias.haug@u.nus.edu
PDF

Phys. Rev. Lett. 133, 050603 – Published 31 July, 2024

DOI: https://doi.org/10.1103/PhysRevLett.133.050603

Abstract

Generalization is the ability of machine learning models to make accurate predictions on new data by learning from training data. However, understanding generalization of quantum machine learning models has been a major challenge. Here, we introduce the data quantum Fisher information metric (DQFIM). It describes the capacity of variational quantum algorithms depending on variational ansatz, training data, and their symmetries. We apply the DQFIM to quantify circuit parameters and training data needed to successfully train and generalize. Using the dynamical Lie algebra, we explain how to generalize using a low number of training states. Counterintuitively, breaking symmetries of the training data can help to improve generalization. Finally, we find that out-of-distribution generalization, where training and testing data are drawn from different data distributions, can be better than using the same distribution. Our work provides a useful framework to explore the power of quantum machine learning models.

View figure in article

Physics Subject Headings (PhySH)

Article Text

Supplemental Material

References (99)

  1. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, Quantum machine learning, Nature (London) 549, 195 (2017).
  2. K. Poland, K. Beer, and T. J. Osborne, No free lunch for quantum machine learning, arXiv:2003.14103.
  3. M. C. Caro and I. Datta, Pseudo-dimension of quantum circuits, Quantum Mach. Intell. 2, 14 (2020).
  4. A. Abbas, D. Sutter, C. Zoufal, A. Lucchi, A. Figalli, and S. Woerner, The power of quantum neural networks, Nat. Comput. Sci. 1, 403 (2021).
  5. A. Abbas, D. Sutter, A. Figalli, and S. Woerner, Effective dimension of machine learning models, arXiv:2112.04807.
  6. K. Sharma, M. Cerezo, Z. Holmes, L. Cincio, A. Sornborger, and P. J. Coles, Reformulation of the no-free-lunch theorem for entangled datasets, Phys. Rev. Lett. 128, 070501 (2022).
  7. L. Banchi, J. Pereira, and S. Pirandola, Generalization in quantum machine learning: A quantum information standpoint, PRX Quantum 2, 040321 (2021).
  8. M. C. Caro, H.-Y. Huang, N. Ezzell, J. Gibbs, A. T. Sornborger, L. Cincio, P. J. Coles, and Z. Holmes, Out-of-distribution generalization for learning quantum dynamics, Nat. Commun. 14, 3751 (2023).
  9. E. Peters and M. Schuld, Generalization despite overfitting in quantum machine learning models, Quantum 7, 1210 (2023).
  10. J. Gibbs, Z. Holmes, M. C. Caro, N. Ezzell, H.-Y. Huang, L. Cincio, A. T. Sornborger, and P. J. Coles, Dynamical simulation via quantum machine learning with provable generalization, Phys. Rev. Res. 6, 013241 (2024).
  11. T. Volkoff, Z. Holmes, and A. Sornborger, Universal compiling and (no-) free-lunch theorems for continuous-variable quantum learning, PRX Quantum 2, 040327 (2021).
  12. H. Cai, Q. Ye, and D.-L. Deng, Sample complexity of learning parametric quantum circuits, Quantum Sci. Technol. 7, 025014 (2022).
  13. C. M. Popescu, Learning bounds for quantum circuits in the agnostic setting, Quantum Inf. Process. 20, 286 (2021).
  14. M. C. Caro, E. Gil-Fuster, J. J. Meyer, J. Eisert, and R. Sweke, Encoding-dependent generalization bounds for parametrized quantum circuits, Quantum 5, 582 (2021).
  15. K. Bu, D. E. Koh, L. Li, Q. Luo, and Y. Zhang, Statistical complexity of quantum circuits, Phys. Rev. A 105, 062431 (2022).
  16. J. Bowles, V. J. Wright, M. Farkas, N. Killoran, and M. Schuld, Contextuality and inductive bias in quantum machine learning, arXiv:2302.01365.
  17. Y. Du, Y. Yang, D. Tao, and M.-H. Hsieh, Problem-dependent power of quantum neural networks on multi-class classification, Phys. Rev. Lett. 131, 140601 (2023).
  18. K. Bu, D. E. Koh, L. Li, Q. Luo, and Y. Zhang, Effects of quantum resources and noise on the statistical complexity of quantum circuits, Quantum Sci. Technol. 8, 025013 (2023).
  19. K. Gili, M. Mauri, and A. Perdomo-Ortiz, Evaluating generalization in classical and quantum generative models, arXiv:2201.08770.
  20. A. Bisio, G. Chiribella, G. M. D’Ariano, S. Facchini, and P. Perinotti, Optimal quantum learning of a unitary transformation, Phys. Rev. A 81, 032324 (2010).
  21. I. Marvian and S. Lloyd, Universal quantum emulator, arXiv:1606.02734.
  22. K. Bharti, A. Cervera-Lierta, T. H. Kyaw, T. Haug, S. Alperin-Lea, A. Anand, M. Degroote, H. Heimonen, J. S. Kottmann, T. Menke, W.-K. Mok, S. Sim, L.-C. Kwek, and A. Aspuru-Guzik, Noisy intermediate-scale quantum algorithms, Rev. Mod. Phys. 94, 015004 (2022).
  23. M. Cerezo, A. Arrasmith, R. Babbush, S. C. Benjamin, S. Endo, K. Fujii, J. R. McClean, K. Mitarai, X. Yuan, L. Cincio et al., Variational quantum algorithms, Nat. Rev. Phys. 3, 625 (2021).
  24. S. Xue, Y. Liu, Y. Wang, P. Zhu, C. Guo, and J. Wu, Variational quantum process tomography of unitaries, Phys. Rev. A 105, 032427 (2022).
  25. V. Gebhart, R. Santagati, A. A. Gentile, E. M. Gauger, D. Craig, N. Ares, L. Banchi, F. Marquardt, L. Pezzè, and C. Bonato, Learning quantum systems, Nat. Rev. Phys. 5, 141 (2023).
  26. B. T. Kiani, S. Lloyd, and R. Maity, Learning unitaries by gradient descent, arXiv:2001.11897.
  27. Z. Yu, X. Zhao, B. Zhao, and X. Wang, Optimal quantum dataset for learning a unitary transformation, Phys. Rev. Appl. 19, 034017 (2023).
  28. E. Farhi and H. Neven, Classification with quantum neural networks on near term processors, arXiv:1802.06002.
  29. M. Schuld, A. Bocharov, K. M. Svore, and N. Wiebe, Circuit-centric quantum classifiers, Phys. Rev. A 101, 032308 (2020).
  30. S. Khatri, R. LaRose, A. Poremba, L. Cincio, A. T. Sornborger, and P. J. Coles, Quantum-assisted quantum compiling, Quantum 3, 140 (2019).
  31. N. Ezzell, E. M. Ball, A. U. Siddiqui, M. M. Wilde, A. T. Sornborger, P. J. Coles, and Z. Holmes, Quantum mixed state compiling, Quantum Sci. Technol. 8, 035001 (2023).
  32. B. Coyle, D. Mills, V. Danos, and E. Kashefi, The Born supremacy: Quantum advantage and training of an Ising born machine, npj Quantum Inf. 6, 60 (2020).
  33. K. Gili, M. Hibat-Allah, M. Mauri, C. Ballance, and A. Perdomo-Ortiz, Do quantum circuit born machines generalize?, Quantum Sci. Technol. 8, 035021 (2023).
  34. C. Cirstoiu, Z. Holmes, J. Iosue, L. Cincio, P. J. Coles, and A. Sornborger, Variational fast forwarding for quantum simulation beyond the coherence time, npj Quantum Inf. 6, 82 (2020).
  35. J. Gibbs, K. Gili, Z. Holmes, B. Commeau, A. Arrasmith, L. Cincio, P. J. Coles, and A. Sornborger, Long-time simulations for fixed input states on quantum hardware, npj Quantum Inf. 8, 135 (2022).
  36. J. Romero, J. P. Olson, and A. Aspuru-Guzik, Quantum autoencoders for efficient compression of quantum data, Quantum Sci. Technol. 2, 045001 (2017).
  37. H. Zhang, L. Wan, T. Haug, W.-K. Mok, S. Paesani, Y. Shi, H. Cai, L. K. Chin, M. F. Karim, L. Xiao et al., Resource-efficient high-dimensional subspace teleportation with a quantum autoencoder, Sci. Adv. 8, eabn9783 (2022).
  38. L. Leone, S. F. E. Oliviero, S. Piemontese, S. True, and A. Hamma, Retrieving information from a black hole using quantum machine learning, Phys. Rev. A 106, 062434 (2022).
  39. M. C. Caro, H.-Y. Huang, M. Cerezo, K. Sharma, A. Sornborger, L. Cincio, and P. J. Coles, Generalization in quantum machine learning from few training data, Nat. Commun. 13, 4919 (2022).
  40. E. Gil-Fuster, J. Eisert, and C. Bravo-Prieto, Understanding quantum machine learning also requires rethinking generalization, Nat. Commun. 15, 2277 (2024).
  41. L. Schatzki, M. Larocca, Q. T. Nguyen, F. Sauvage, and M. Cerezo, Theoretical guarantees for permutation-equivariant quantum neural networks, npj Quantum Inf. 10, 12 (2024).
  42. M. Ragone, P. Braccia, Q. T. Nguyen, L. Schatzki, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, Representation theory for geometric quantum machine learning, arXiv:2210.07980.
  43. Q. T. Nguyen, L. Schatzki, P. Braccia, M. Ragone, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, Theory for equivariant quantum neural networks, PRX Quantum 5, 020328 (2024).
  44. H. Zheng, Z. Li, J. Liu, S. Strelchuk, and R. Kondor, Speeding up learning quantum states through group equivariant convolutional quantum ansätze, PRX Quantum 4, 020327 (2023).
  45. J. J. Meyer, M. Mularski, E. Gil-Fuster, A. A. Mele, F. Arzani, A. Wilms, and J. Eisert, Exploiting symmetry in variational quantum machine learning, PRX Quantum 4, 010328 (2023).
  46. M. Larocca, F. Sauvage, F. M. Sbahi, G. Verdon, P. J. Coles, and M. Cerezo, Group-invariant quantum machine learning, PRX Quantum 3, 030341 (2022).
  47. F. Sauvage, M. Larocca, P. J. Coles, and M. Cerezo, Building spatial symmetries into parametrized quantum circuits for faster training, Quantum Sci. Technol. 9 (2024).
  48. A. Skolik, M. Cattelan, S. Yarkoni, T. Bäck, and V. Dunjko, Equivariant quantum circuits for learning on weighted graphs, npj Quantum Inf. 9, 47 (2023).
  49. T. Haug, K. Bharti, and M. S. Kim, Capacity and quantum geometry of parametrized quantum circuits, PRX Quantum 2, 040309 (2021).
  50. K. Bu, D. E. Koh, L. Li, Q. Luo, and Y. Zhang, Rademacher complexity of noisy quantum circuits, arXiv:2103.03139.
  51. E. R. Anschuetz, A. Bauer, B. T. Kiani, and S. Lloyd, Efficient classical algorithms for simulating symmetric quantum systems, Quantum 7, 1189 (2023).
  52. H.-Y. Huang, M. Broughton, M. Mohseni, R. Babbush, S. Boixo, H. Neven, and J. R. McClean, Power of data in quantum machine learning, Nat. Commun. 12, 1 (2021).
  53. Y. Liu, S. Arunachalam, and K. Temme, A rigorous and robust quantum speed-up in supervised machine learning, Nat. Phys. 17, 1013 (2021).
  54. H.-Y. Huang, R. Kueng, G. Torlai, V. V. Albert, and J. Preskill, Provably efficient machine learning for quantum many-body problems, Science 377, eabk3333 (2022).
  55. J. Liu, M. Liu, J.-P. Liu, Z. Ye, Y. Wang, Y. Alexeev, J. Eisert, and L. Jiang, Towards provably efficient quantum algorithms for large-scale machine-learning models, Nat. Commun. 15, 434 (2024).
  56. P. L. Bartlett, D. J. Foster, and M. J. Telgarsky, Spectrally-normalized margin bounds for neural networks, Adv. Neural Inf. Process. Syst. 30, 6240 (2017), http://papers.nips.cc/paper/7204-spectrally-normalized.
  57. Y. Jiang, B. Neyshabur, H. Mobahi, D. Krishnan, and S. Bengio, Fantastic generalization measures and where to find them, arXiv:1912.02178.
  58. T. Liang, T. Poggio, A. Rakhlin, and J. Stokes, Fisher-Rao metric, geometry, and complexity of neural networks, in Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (PMLR, Barcelona, 2019), pp. 888–896.
  59. M. Larocca, N. Ju, D. García-Martín, P. J. Coles, and M. Cerezo, Theory of overparametrization in quantum neural networks, NATO ASI series Series F, Computer and system sciences 3, 542 (2023).
  60. J. J. Meyer, Fisher information in noisy intermediate-scale quantum applications, Quantum 5, 539 (2021).
  61. D. García-Martín, M. Larocca, and M. Cerezo, Effects of noise on the overparametrization of quantum neural networks, Phys. Rev. Res. 6, 013295 (2024).
  62. R. Chakrabarti and H. Rabitz, Quantum control landscapes, Int. Rev. Phys. Chem. 26, 671 (2007).
  63. M. S. Rudolph, S. Lerch, S. Thanasilp, O. Kiss, S. Vallecorsa, M. Grossi, and Z. Holmes, Trainability barriers and opportunities in quantum generative modeling, arXiv:2305.02881.
  64. A. Pérez-Salinas, A. Cervera-Lierta, E. Gil-Fuster, and J. I. Latorre, Data re-uploading for a universal quantum classifier, Quantum 4, 226 (2020).
  65. S. Jerbi, L. J. Fiderer, H. Poulsen Nautrup, J. M. Kübler, H. J. Briegel, and V. Dunjko, Quantum machine learning beyond kernel methods, Nat. Commun. 14, 517 (2023).
  66. K. Mitarai, M. Negoro, M. Kitagawa, and K. Fujii, Quantum circuit learning, Phys. Rev. A 98, 032309 (2018).
  67. M. A. Nielsen and I. L Chuang, Quantum Computation and Quantum Information, 10th Anniversary Edition (Cambridge Univ. Press, 2011).
  68. See Supplemental Material at http://link.aps.org/supplemental/10.1103/PhysRevLett.133.050603, which includes Refs. [69–75], for detailed derivations, as well as additional theoretical and numerical results.
  69. R. Cheng, Quantum geometric tensor (Fubini-Study metric) in simple quantum system: A pedagogical introduction, arXiv:1012.1337.
  70. Y. Li and S. C. Benjamin, Efficient variational quantum simulator incorporating active error minimization, Phys. Rev. X 7, 021050 (2017).
  71. X. Yuan, S. Endo, Q. Zhao, Y. Li, and S. C. Benjamin, Theory of variational quantum simulation, Quantum 3, 191 (2019).
  72. D. d’Alessandro, Introduction to Quantum Control and Dynamics (Chapman and Hall/CRC, London, 2021).
  73. J. Werschnik and E. Gross, Quantum optimal control theory, J. Phys. B 40, R175 (2007).
  74. N. Khaneja, T. Reiss, C. Kehlet, T. Schulte-Herbrüggen, and S. J. Glaser, Optimal control of coupled spin dynamics: Design of nmr pulse sequences by gradient ascent algorithms, J. Magn. Reson. 172, 296 (2005).
  75. E. Recio-Armengol, J. Eisert, and J. J. Meyer, Single-shot quantum machine learning, arXiv:2406.13812.
  76. J. Liu, H. Yuan, X.-M. Lu, and X. Wang, Quantum Fisher information matrix and multiparameter estimation, J. Phys. A 53, 023001 (2020).
  77. H. A. Rabitz, M. M. Hsieh, and C. M. Rosenthal, Quantum optimally controlled transition landscapes, Science 303, 1998 (2004).
  78. M. Bukov, A. G. R. Day, D. Sels, P. Weinberg, A. Polkovnikov, and P. Mehta, Reinforcement learning in different phases of quantum control, Phys. Rev. X 8, 031086 (2018).
  79. E. R. Anschuetz, Critical points in quantum generative models, arXiv:2109.06957.
  80. X. You, S. Chakrabarti, and X. Wu, A convergence theory for over-parametrized variational quantum eigensolvers, arXiv:2205.12481.
  81. J. Polcari, Representing unitary matrices by independent parameters, Technical Report (Working Paper, Rev 0, 2016).
  82. R. Fletcher, Practical Methods of Optimization (John Wiley & Sons, New York, 2013).
  83. J. R. Johansson, P. D. Nation, and F. Nori, Qutip: An open-source python framework for the dynamics of open quantum systems, Comput. Phys. Commun. 183, 1760 (2012).
  84. R. Wiersema, E. Kökcü, A. F. Kemper, and B. N. Bakalov, Classification of dynamical lie algebras for translation-invariant 2-local spin systems in one dimension, arXiv:2309.05690.
  85. E. Kökcü, D. Camps, L. B. Oftelie, J. K. Freericks, W. A. de Jong, R. Van Beeumen, and A. F. Kemper, Algebraic compression of quantum circuits for Hamiltonian evolution, Phys. Rev. A 105, 032420 (2022).
  86. E. Kökcü, T. Steckmann, Y. Wang, J. K. Freericks, E. F. Dumitrescu, and A. F. Kemper, Fixed depth Hamiltonian simulation via cartan decomposition, Phys. Rev. Lett. 129, 070501 (2022).
  87. J. Kim, J. Kim, and D. Rosa, Universal effectiveness of high-depth circuits in variational eigenproblems, Phys. Rev. Res. 3, 023203 (2021).
  88. E. Campos, A. Nasrallah, and J. Biamonte, Abrupt transitions in variational quantum circuit training, Phys. Rev. A 103, 032607 (2021).
  89. J. Kim and Y. Oz, Quantum energy landscape and circuit optimization, Phys. Rev. A 106, 052424 (2022).
  90. F. Sauvage, M. Larocca, P. J. Coles, and M. Cerezo, Building spatial symmetries into parametrized quantum circuits for faster training, Quantum Sci. Technol. 9, 015029 (2024).
  91. E. Fontana, D. Herman, S. Chakrabarti, N. Kumar, R. Yalovetzky, J. Heredge, S. H. Sureshbabu, and M. Pistoia, The adjoint is all you need: Characterizing barren plateaus in quantum ansätze, arXiv:2309.07902.
  92. M. Ragone, B. N. Bakalov, F. Sauvage, A. F. Kemper, C. O. Marrero, M. Larocca, and M. Cerezo, A unified theory of barren plateaus for deep parametrized quantum circuits, arXiv:2309.09342.
  93. K. M. Nakanishi, K. Mitarai, and K. Fujii, Subspace-search variational quantum eigensolver for excited states, Phys. Rev. Res. 1, 033062 (2019).
  94. T. Haug, Generalization with quantum geometry, https://github.com/txhaug/geometric_generalization.
  95. A. Mari, T. R. Bromley, and N. Killoran, Estimating the gradient and higher-order derivatives on quantum hardware, Phys. Rev. A 103, 012405 (2021).
  96. J. Haferkamp, P. Faist, N. B. Kothakonda, J. Eisert, and N. Yunger Halpern, Linear growth of quantum circuit complexity, Nat. Phys. 18, 528 (2022).
  97. M. Schuld and N. Killoran, Quantum machine learning in feature Hilbert spaces, Phys. Rev. Lett. 122, 040504 (2019).
  98. T. Haug, C. N. Self, and M. S. Kim, Quantum machine learning of large datasets using randomized measurements, Mach. Learn. 4, 015005 (2023).
  99. J. Stokes, J. Izaac, N. Killoran, and G. Carleo, Quantum natural gradient, Quantum 4, 269 (2020).

Outline

Information

Phys. Rev. Lett. 133, 050603– Published 31 July, 2024
  • Received 30 March 2023
  • Revised 27 June 2024
  • Accepted 3 July 2024
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