- 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
  • Letter
  • Open Access

Scrambling ability of quantum neural network architectures

Yadong Wu1, Pengfei Zhang2,3,*, and Hui Zhai1,†

  • 1Institute for Advanced Study, Tsinghua University, Beijing 100084, China
  • 2Institute for Quantum Information and Matter, California Institute of Technology, Pasadena, California 91125, USA
  • 3Walter Burke Institute for Theoretical Physics, California Institute of Technology, Pasadena, California 91125, USA

  • *pengfeizhang.physics@gmail.com
  • †hzhai@tsinghua.edu.cn
PDF

Phys. Rev. Research 3, L032057 – Published 3 September, 2021

DOI: https://doi.org/10.1103/PhysRevResearch.3.L032057

Abstract

In this Letter, we propose a guiding principle for how to design the architecture of a quantum neural network in order to achieve a high learning efficiency. This principle is inspired by the equivalence between extracting information from the input state to the readout qubit and scrambling information from the readout qubit to input qubits. We characterize the quantum information scrambling by operator size growth. By Haar random averaging over operator sizes, we propose an averaged operator size to describe the information scrambling ability of a given quantum neural network architecture. The key conjecture of this Letter is that this quantity is positively correlated with the learning efficiency of this architecture. To support this conjecture, we consider several different architectures, and we also consider two typical learning tasks. One is a regression task of a quantum problem, and the other is a classification task on classical images. In both cases, we find that, for the architecture with a larger averaged operator size, the loss function decreases faster or the prediction accuracy increases faster as the training epoch increases, which means higher learning efficiency. Our results can be generalized to more complicated quantum versions of machine learning algorithms.

View figure in article

Physics Subject Headings (PhySH)

Article Text

Supplemental Material

References (55)

  1. I. Goodfellow, Y. Bengio, and A. Couville, Deep Learning (MIT Press, Cambridge, MA, 2016).
  2. J. Preskill, Quantum computing in the NISQ era and beyond, Quantum 2, 79 (2018).
  3. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, Quantum machine learning, Nature (London) 549, 195 (2017).
  4. M. Broughton, G. Verdon, T. McCourt, A. J. Martinez, J. H. Yoo, S. V. Isakov, P. Massey, R. Halavati, M. Y. Niu, A. Zlokapa, E. Peters, O. Lockwood, A. Skolik, S. Jerbi, V. Dunjko, M. Leib, M. Streif, D. V. Dollen, H. Chen, S. Cao, R. Wiersema, H.-Y. Huang, J. R. McClean, R. Babbush, S. Boixo, D. Bacon, A. K. Ho, H. Neven, and M. Mohseni, TensorFlow quantum: A software framework for quantum machine learning, arXiv:2003.02989.
  5. L. Lamata, Quantum machine learning and quantum biomimetics: A perspective, Mach. Learn.: Sci. Technol. 1, 033002 (2020)
  6. E. Farhi, and H. Neven, Classification with quantum neural networks on near term processors, arXiv:1802.06002.
  7. M. Schuld, A. Bocharov, Krysta M. Svore, and N. Wiebe, Circuit-centric quantum classifiers, Phys. Rev. A 101, 032308 (2020).
  8. E. Grant, M. Benedetti, S. Cao, A. Hallam, J. Lockhart, V. Stojevic, A. G. Green, and S. Severini, Hierarchical quantum classifiers, npj Quantum Inf. 4, 65 (2018).
  9. J.-G. Liu and L. Wang, Differentiable learning of quantum circuit Born machines, Phys. Rev. A 98, 062324 (2018).
  10. J. Zeng, Y. Wu, Jin-G. Liu, L. Wang, and J. Hu, Learning and inference on generative adversarial quantum circuits, Phys. Rev. A 99, 052306 (2019).
  11. X. Liang, Y. Wu and H. Zhai, The quantum cocktail party problem, Sci. China: Phys., Mech. Astron., 63, 250362 (2020).
  12. M. Benedetti, D. Garcia-Pintos, O. Perdomo, V. Leyton-Ortega, Y. Nam, and A. PerdomoOrtiz, A generative modeling approach for benchmarking and training shallow quantum circuits, npj Quantum Inf. 5, 45 (2019).
  13. M. J. S. Beach, R. G. Melko, T. Grover, and T. H. Hsieh, Making trotters sprint: A variational imaginary time ansatz for quantum many-body systems, Phys. Rev. B 100, 094434 (2019).
  14. S. Ghosh, T. Paterek, and Timothy C. H. Liew, Quantum Neuromorphic Platform for Quantum State Preparation, Phys. Rev. Lett 123, 260404 (2019).
  15. T. Krisnanda, S. Ghosh, T. Peterek, and Timothy C. H. Liew, Creating and concentrating quantum resource states in noisy environments using a quantum neural network, Neural Networks 136, 141-151 (2021).
  16. Y. Du, M.-H. Hsieh, T. Liu, and D. Tao, Expressive power of parametrized quantum circuits, Phys. Rev. Research 2, 033125 (2020).
  17. W. Huggins, P. Patil, B. Mitchell, K. B. Whaley, and E. M. Stoudenmire, Towards quantum machine learning with tensor networks, Quantum Sci. Technol. 4, 024001 (2019).
  18. K. Beer, D. Bondarenko, T. Farrelly, T. J. Osborne, R. Salzmann, and R. Wolf, Efficient Learning for Deep Quantum Neural Networks, Nat. Commun. 11, 808 (2020).
  19. M. Benedetti, J. Realpe-Gómez, R. Biswas, and A. Perdomo-Ortiz, Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models, Phys. Rev. X 7, 041052 (2017).
  20. J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, Barren plateaus in quantum neural network training landscapes, Nat. Commun. 9, 4812 (2018).
  21. K. Mitarai, M. Negoro, M. Kitagawa, and K. Fujii, Quantum circuit learning, Phys. Rev. A 98, 032309 (2018).
  22. E. Torrontegui, and J. J. García-Ripoll, Unitary quantum perceptron as efficient universal approximator, Europhys. Lett. 125, 30004 (2019).
  23. S. Ghosh, T. Krisnanda, T. Peterek, and T. C. H. Liew, Realising and compressing quantum circuits with quantum reservoir computing, Commun. Phys. 4, 105 (2021).
  24. I. Cong, S. Choi, and M. D. Lukin, Quantum convolutional neural networks, Nat. Phys. 15, 1273 (2019).
  25. M. Henderson, S. Shakya, S. Pradhan, and T. Cook, Quanvolutional neural networks: powering image recognition with quantum circuits, arXiv:1904.04767.
  26. S. Oh, J. Choi, and J. Kim, A tutorial on quantum convolutional neural networks (QCNN), arXiv:2009.09423.
  27. J. Bausch, Recurrent quantum neural networks, ” Advances in Neural Information Processing Systems 33 (NeurIPS 2020).
  28. L. Behera, I. Kar, and A. C. Elitzur, Recurrent quantum neural network and its applications, The Emerging Physics of Consciousness, edited by J. A. Tuszynski (The Frontiers Collection, Springer, Berlin, Heidelberg, 2006).
  29. J. Romero, J. P. Olson, and A. Aspuru-Guzik, Quantum autoencoders for efficient compression of quantum data, Quantum Sci. Technol. 2, 045001 (2017).
  30. D. Bondarenko, and P. Feldmann, Quantum Autoencoders to Denoise Quantum Data, Phys. Rev. Lett. 124, 130502 (2020).
  31. A. Pepper, N. Tischler, and G. J. Pryde, Experimental Realization of a Quantum Autoencoder: The Compression of Qutrits via Machine Learning, Phys. Rev. Lett. 122, 060501 (2019).
  32. S. H. Shenker, and D. Stanford, Black holes and the butterfly effect, J. High Energy Phys. 03 (2014) 067.
  33. D. A. Roberts, D. Stanford, and L. Susskind, Localized shocks, J. High Energy Phys. 03 (2015) 051.
  34. D. A. Roberts, and D. Stanford, Diagnosing Chaos Using Four-Point Functions in Two-Dimensional Conformal Field Theory, Phys. Rev. Lett. 115, 131603 (2015).
  35. J. Maldacena, S. H. Shenker, and D. Stanford, A bound chaos, J. High Energy Phys. 08 (2016) 106.
  36. P. Hosur, X.-L. Qi, and D. Roberts, Chaos in quantum channels, J. High Energy Phys. 02 (2016) 004.
  37. R. Fan, P. Zhang, Huitao Shen and H. Zhai, Out-of-Time-Order correlation for many-body localization, Sci. Bulletin 62, 707 (2017).
  38. M. Rangamani, and M. Rota, Entanglement structures in qubit systems, J. Phys. A: Math. Theor. 48, 385301 (2015).
  39. A. Kitaev, and J. Preskill, Topological Entanglement Entropy, Phys. Rev. Lett. 96, 110404 (2006).
  40. M. Levin, and X.-G. Wen, Detecting Topological Order in a Ground State Wave Function, Phys. Rev. Lett. 96, 110405 (2006).
  41. C. Sünderhauf, L. Piroli, X.-L. Qi, N. Schuch, and J. I. Cirac, Quantum chaos in the Brownian SYK model with large finite N : OTOCs and tripartite information, J. High Energy Phys. 11 (2019) 038.
  42. D. A. Roberts, D. Stanford, and A. Streicher, Operator growth in the SYK model, J. High Energy Phys. 06 (2018) 122.
  43. A. Nahum, S. Vijay, and J. Haah, Operator Spreading in Random Unitary Circuits, Phys. Rev. X 8, 021014 (2018).
  44. C. W. von Keyserlingk, T. Rakovszky, F. Pollmann, and S. L. Sondhi, Operator Hydrodynamics, OTOCs, and Entanglement Growth in Systems without Conservation Laws, Phys. Rev. X 8, 021013 (2018).
  45. V. Khemani, A. Vishwanath, and D. A. Huse, Operator Spreading and the Emergence of Dissipative Hydrodynamics under Unitary Evolution with Conservation Laws, Phys. Rev. X 8, 031057 (2018).
  46. T. Rakovszky, F. Pollmann, and C. W. V. Keyserlingk, Diffusive Hydrodynamics of Out-of-Time-Ordered Correlators with Charge Conservation, Phys. Rev. X 8, 031058 (2018).
  47. X. Chen, and T. Zhou, Operator scrambling and quantum chaos, arXiv:1804.08655.
  48. A. Lucas, Operator Size at Finite Temperature and Planckian Bounds on Quantum Dynamics, Phys. Rev. Lett. 122, 216601 (2019).
  49. S. Xu, and B. Swingle, Locality, Quantum Fluctuations, and Scrambling, Phys. Rev. X 9, 031048 (2019).
  50. X.-L. Qi, and A. Streicher, Quantum epidemiology: operator growth, thermal effects and SYK, J. High Energy Phys. 08 (2019) 012.
  51. S. Xu, and B. Swingle, Accessing scrambling using matrix product operators, Nat. Phys. 16, 199 (2020).
  52. Y. D. Lensky, X.-L. Qi, and P. Zhang, Size of bulk fermions in the SYK model, J. High Energy Phys. 10 (2020) 053.
  53. H. Shen, P. Zhang, Y.-Z. You, and H. Zhai, Information Scrambling in Quantum Neural Networks, Phys. Rev. Lett. 124, 200504 (2020).
  54. See Supplemental Material at http://link.aps.org/supplemental/10.1103/PhysRevResearch.3.L032057 for details of training data encoding, general architectures, saturation of operator size, noise against, and training process.
  55. For supercube circuits (S), we set the last unit Û1 the same as the hyperbolic unit Fig. 1. Other units Ûl≥2 are chosen such that the circuit ÛL⋯Û2 repeats the structure of Fig. 1 and each unit contains seven two-qubit gates. Such a structure eliminates redundant gates in U1 and is found to be optimal for the operator size growth.

Outline

Information

Phys. Rev. Research 3, L032057– Published 3 September, 2021
  • Received 30 November 2020
  • Revised 1 March 2021
  • Accepted 23 August 2021
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