- 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

Design of expressive and trainable pulse-based quantum machine learning models

Han-Xiao Tao, Xin Wang, and Re-Bing Wu*

  • Center for Intelligent and Networked Systems, Department of Automation, Tsinghua University, Beijing 100084, China

  • *Contact author: rbwu@tsinghua.edu.cn
PDF

Phys. Rev. Research 8, 013338 – Published 30 March, 2026

DOI: https://doi.org/10.1103/gvj4-kqwd

Abstract

Pulse-based quantum machine learning (QML) has emerged as a promising paradigm in quantum artificial intelligence due to its exceptional hardware efficiency. For real-world applications, it is crucial that pulse-based models are both expressive and trainable. Previous studies have shown that pulse-based models operating under dynamical symmetry can be effectively trained, benefiting from a favorable loss landscape devoid of barren plateaus. However, this approach may lead to uncontrollability, which can limit expressivity if the model is poorly designed. In this paper, we explore the conditions necessary for pulse-based QML models to maintain both expressivity and trainability. We present a key requirement involving the system's initial state, the measurement observable, and the underlying dynamical symmetry Lie algebra, supported by numerical simulations. Our results provide a comprehensive framework for the design of practical pulse-based QML models that strike a good balance between expressivity and trainability.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (63)

  1. F. Arute, K. Arya, R. Babbush, D. Bacon, J. C. Bardin, R. Barends, R. Biswas, S. Boixo, F. G. Brandao, D. A. Buell, et al., Quantum supremacy using a programmable superconducting processor, Nature (London) 574, 505 (2019).
  2. H.-S. Zhong, H. Wang, Y.-H. Deng, M.-C. Chen, L.-C. Peng, Y.-H. Luo, J. Qin, D. Wu, X. Ding, Y. Hu, et al., Quantum computational advantage using photons, Science 370, 1460 (2020).
  3. Q. Zhu, S. Cao, F. Chen, M.-C. Chen, X. Chen, T.-H. Chung, H. Deng, Y. Du, D. Fan, M. Gong, et al., Quantum computational advantage via 60-qubit 24-cycle random circuit sampling, Sci. Bull. 67, 240 (2022).
  4. H.-Y. Huang, M. Broughton, J. Cotler, S. Chen, J. Li, M. Mohseni, H. Neven, R. Babbush, R. Kueng, J. Preskill, et al., Quantum advantage in learning from experiments, Science 376, 1182 (2022).
  5. S. Endo, Z. Cai, S. C. Benjamin, and X. Yuan, Hybrid quantum-classical algorithms and quantum error mitigation, J. Phys. Soc. Jpn. 90, 032001 (2021).
  6. A. Callison and N. Chancellor, Hybrid quantum-classical algorithms in the noisy intermediate-scale quantum era and beyond, Phys. Rev. A 106, 010101 (2022).
  7. E. Farhi and H. Neven, Classification with quantum neural networks on near term processors, arXiv:1802.06002.
  8. 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).
  9. R.-B. Wu, X. Cao, P. Xie, and Y.-x. Liu, End-to-end quantum machine learning implemented with controlled quantum dynamics, Phys. Rev. Appl. 14, 064020 (2020).
  10. A. B. Magann, C. Arenz, M. D. Grace, T.-S. Ho, R. L. Kosut, J. R. McClean, H. A. Rabitz, and M. Sarovar, From pulses to circuits and back again: A quantum optimal control perspective on variational quantum algorithms, PRX Quantum 2, 010101 (2021).
  11. A. Choquette, A. Di Paolo, P. K. Barkoutsos, D. Sénéchal, I. Tavernelli, and A. Blais, Quantum-optimal-control-inspired ansatz for variational quantum algorithms, Phys. Rev. Res. 3, 023092 (2021).
  12. O. R. Meitei, B. T. Gard, G. S. Barron, D. P. Pappas, S. E. Economou, E. Barnes, and N. J. Mayhall, Gate-free state preparation for fast variational quantum eigensolver simulations, npj Quantum Inf. 7, 155 (2021).
  13. R. De Keijzer, O. Tse, and S. Kokkelmans, Pulse based variational quantum optimal control for hybrid quantum computing, Quantum 7, 908 (2023).
  14. K. M. Sherbert, H. Amer, S. E. Economou, E. Barnes, and N. J. Mayhall, Parametrization and optimizability of pulse-level variational quantum eigensolvers, Phys. Rev. Appl. 23, 024036 (2025).
  15. L. Broers and L. Mathey, Mitigated barren plateaus in the time-nonlocal optimization of analog quantum-algorithm protocols, Phys. Rev. Res. 6, 013076 (2024).
  16. Y. Wang, Y. Ding, F. A. Cárdenas-López, and X. Chen, Pulse-based variational quantum optimization and metalearning in superconducting circuits, Phys. Rev. Appl. 22, 024009 (2024).
  17. X. Pan, X. Cao, W. Wang, Z. Hua, W. Cai, X. Li, H. Wang, J. Hu, Y. Song, D.-L. Deng, et al., Experimental quantum end-to-end learning on a superconducting processor, npj Quantum Inf. 9, 18 (2023).
  18. A. Melo, N. Earnest-Noble, and F. Tacchino, Pulse-efficient quantum machine learning, Quantum 7, 1130 (2023).
  19. M. M. Ibrahim, H. Mohammadbagherpoor, C. Rios, N. T. Bronn, and G. T. Byrd, Evaluation of parameterized quantum circuits with cross-resonance pulse-driven entanglers, IEEE Trans. Quantum Eng. 3, 1 (2022).
  20. D. J. Egger, C. Capecci, B. Pokharel, P. K. Barkoutsos, L. E. Fischer, L. Guidoni, and I. Tavernelli, Pulse variational quantum eigensolver on cross-resonance-based hardware, Phys. Rev. Res. 5, 033159 (2023).
  21. Z. Liang, J. Cheng, Z. Song, H. Ren, R. Yang, K. Liu, P. Kogge, T. Li, Y. Ding, and Y. Shi, Towards advantages of parameterized quantum pulses, arXiv:2304.09253.
  22. A. Asthana, C. Liu, O. R. Meitei, S. E. Economou, E. Barnes, and N. J. Mayhall, Leakage reduces device coherence demands for pulse-level molecular simulations, Phys. Rev. Appl. 19, 064071 (2023).
  23. A. Michel, S. Grijalva, L. Henriet, C. Domain, and A. Browaeys, Blueprint for a digital-analog variational quantum eigensolver using Rydberg atom arrays, Phys. Rev. A 107, 042602 (2023).
  24. D. Rabinovich, S. Adhikary, E. Campos, V. Akshay, E. Anikin, R. Sengupta, O. Lakhmanskaya, K. Lakhmanskiy, and J. Biamonte, Ion-native variational ansatz for quantum approximate optimization, Phys. Rev. A 106, 032418 (2022).
  25. H.-X. Tao, J. Hu, and R.-B. Wu, Unleashing the expressive power of pulse-based quantum neural networks, Quantum Mach. Intell. 7, 109 (2025).
  26. V. Havlíček, A. D. Córcoles, K. Temme, A. W. Harrow, A. Kandala, J. M. Chow, and J. M. Gambetta, Supervised learning with quantum-enhanced feature spaces, Nature (London) 567, 209 (2019).
  27. M. Schuld and N. Killoran, Quantum machine learning in feature Hilbert spaces, Phys. Rev. Lett. 122, 040504 (2019).
  28. M. Schuld, Supervised quantum machine learning models are kernel methods, arXiv:2101.11020.
  29. J. Jäger and R. V. Krems, Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines, Nat. Commun. 14, 576 (2023).
  30. S. Lloyd, Almost any quantum logic gate is universal, Phys. Rev. Lett. 75, 346 (1995).
  31. M. Larocca, P. Czarnik, K. Sharma, G. Muraleedharan, P. J. Coles, and M. Cerezo, Diagnosing barren plateaus with tools from quantum optimal control, Quantum 6, 824 (2022).
  32. M. Larocca, S. Thanasilp, S. Wang, K. Sharma, J. Biamonte, P. J. Coles, L. Cincio, J. R. McClean, Z. Holmes, and M. Cerezo, Barren plateaus in variational quantum computing, Nat. Rev. Phys. 7, 174 (2025).
  33. A. Arrasmith, Z. Holmes, M. Cerezo, and P. J. Coles, Equivalence of quantum barren plateaus to cost concentration and narrow gorges, Quantum Sci. Technol. 7, 045015 (2022).
  34. Q. Miao and T. Barthel, Equivalence of cost concentration and gradient vanishing for quantum circuits: An elementary proof in the Riemannian formulation, Quantum Sci. Technol. 9, 045039 (2024).
  35. L. Banchi, D. Burgarth, and M. J. Kastoryano, Driven quantum dynamics: Will it blend? Phys. Rev. X 7, 041015 (2017).
  36. K. Sharma, M. Cerezo, L. Cincio, and P. J. Coles, Trainability of dissipative perceptron-based quantum neural networks, Phys. Rev. Lett. 128, 180505 (2022).
  37. M. Cerezo, A. Sone, T. Volkoff, L. Cincio, and P. J. Coles, Cost function dependent barren plateaus in shallow parametrized quantum circuits, Nat. Commun. 12, 1791 (2021).
  38. S. Wang, E. Fontana, M. Cerezo, K. Sharma, A. Sone, L. Cincio, and P. J. Coles, Noise-induced barren plateaus in variational quantum algorithms, Nat. Commun. 12, 6961 (2021).
  39. A. Arrasmith, M. Cerezo, P. Czarnik, L. Cincio, and P. J. Coles, Effect of barren plateaus on gradient-free optimization, Quantum 5, 558 (2021).
  40. M. Cerezo and P. J. Coles, Higher order derivatives of quantum neural networks with barren plateaus, Quantum Sci. Technol. 6, 035006 (2021).
  41. Z. Holmes, A. Arrasmith, B. Yan, P. J. Coles, A. Albrecht, and A. T. Sornborger, Barren plateaus preclude learning scramblers, Phys. Rev. Lett. 126, 190501 (2021).
  42. Z. Holmes, K. Sharma, M. Cerezo, and P. J. Coles, Connecting ansatz expressibility to gradient magnitudes and barren plateaus, PRX Quantum 3, 010313 (2022).
  43. L. Friedrich and J. Maziero, Quantum neural network cost function concentration dependency on the parametrization expressivity, Sci. Rep. 13, 9978 (2023).
  44. M. Ragone, B. N. Bakalov, F. Sauvage, A. F. Kemper, C. Ortiz Marrero, M. Larocca, and M. Cerezo, A Lie algebraic theory of barren plateaus for deep parameterized quantum circuits, Nat. Commun. 15, 7172 (2024).
  45. E. Fontana, D. Herman, S. Chakrabarti, N. Kumar, R. Yalovetzky, J. Heredge, S. H. Sureshbabu, and M. Pistoia, Characterizing barren plateaus in quantum ansätze with the adjoint representation, Nat. Commun. 15, 7171 (2024).
  46. N. L. Diaz, D. García-Martín, S. Kazi, M. Larocca, and M. Cerezo, Showcasing a barren plateau theory beyond the dynamical Lie algebra, arXiv:2310.11505.
  47. F. J. Gil Vidal and D. O. Theis, Input redundancy for parameterized quantum circuits, Front. Phys. 8, 297 (2020).
  48. T. Goto, Q. H. Tran, and K. Nakajima, Universal approximation property of quantum machine learning models in quantum-enhanced feature spaces, Phys. Rev. Lett. 127, 090506 (2021).
  49. A. Pérez-Salinas, D. López-Núñez, A. García-Sáez, P. Forn-Díaz, and J. I. Latorre, One qubit as a universal approximant, Phys. Rev. A 104, 012405 (2021).
  50. M. Schuld, R. Sweke, and J. J. Meyer, Effect of data encoding on the expressive power of variational quantum-machine-learning models, Phys. Rev. A 103, 032430 (2021).
  51. Z. Yu, H. Yao, M. Li, and X. Wang, Power and limitations of single-qubit native quantum neural networks, in Proceedings of the 36th International Conference on Neural Information Processing Systems (Curran Associates Inc., New York, 2022).
  52. A. Isidori, Nonlinear Control Systems (Springer Science & Business Media, Springer London, 1995).
  53. Z. Liang, J. Cheng, H. Ren, H. Wang, F. Hua, Z. Song, Y. Ding, F. T. Chong, S. Han, X. Qian, et al., NAPA: Intermediate-level variational native-pulse ansatz for variational quantum algorithms, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 43, 1834 (2024).
  54. D. Meirom and S. H. Frankel, Pansatz: Pulse-based ansatz for variational quantum algorithms, Front. Quantum Sci. Technol. 2, 1273581 (2023).
  55. Z. Liang, H. Wang, J. Cheng, Y. Ding, H. Ren, Z. Gao, Z. Hu, D. S. Boning, X. Qian, S. Han, et al., Variational quantum pulse learning, in IEEE International Conference on Quantum Computing and Engineering (QCE) (IEEE, Broomfield, CO, USA, 2022), pp. 556–565.
  56. Z. Liang, Z. Song, J. Cheng, Z. He, J. Liu, H. Wang, R. Qin, Y. Wang, S. Han, X. Qian, et al., Hybrid gate-pulse model for variational quantum algorithms, in 60th ACM/IEEE Design Automation Conference (DAC) (IEEE, San Francisco, California, US, 2023), pp. 1–6.
  57. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  58. F. T. Arecchi, E. Courtens, R. Gilmore, and H. Thomas, Atomic coherent states in quantum optics, Phys. Rev. A 6, 2211 (1972).
  59. X. Zhao, Y. Zhao, M. Li, T. Li, Q. Liu, S. Guo, and X. Yi, A strategy for preparing quantum squeezed states using reinforcement learning, Ann. Phys. (NY) 536, 2400056 (2024).
  60. P. Krantz, M. Kjaergaard, F. Yan, T. P. Orlando, S. Gustavsson, and W. D. Oliver, A quantum engineer's guide to superconducting qubits, Appl. Phys. Rev. 6, 021318 (2019).
  61. R. Wiersema, E. Kökcü, A. F. Kemper, and B. N. Bakalov, Classification of dynamical Lie algebras of 2-local spin systems on linear, circular and fully connected topologies, npj Quantum Inf. 10, 110 (2024).
  62. A. Kandala, A. Mezzacapo, K. Temme, M. Takita, M. Brink, J. M. Chow, and J. M. Gambetta, Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets, Nature (London) 549, 242 (2017).
  63. R.-B. Wu, M. A. Hsieh, and H. Rabitz, Role of controllability in optimizing quantum dynamics, Phys. Rev. A 83, 062306 (2011).

Outline

Information

Phys. Rev. Research 8, 013338– Published 30 March, 2026
  • Received 10 November 2025
  • Accepted 9 February 2026
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