- 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

Metalearning characteristics and dynamics of quantum systems

Lucas Schorling1,*, Pranav Vaidhyanathan1,*, Jonas Schuff2, Miguel J. Carballido3, Dominik Zumbühl3, Gerard Milburn4, Florian Marquardt5,6, Jakob Foerster1, Maike Osborne1 et al.

Natalia Ares1,†

  • *These authors contributed equally to this work.
  • †Contact author: natalia.ares@eng.ox.ac.uk
PDF

Phys. Rev. Research 8, 033248 – Published 31 August, 2026

DOI: https://doi.org/10.1103/6m8t-r5qk

Abstract

While machine learning holds great promise for quantum technologies, most current methods focus on predicting or controlling a specific quantum system. Metalearning approaches, however, can adapt to new systems for which little data are available, by leveraging knowledge obtained from previous data associated with similar systems. In this paper, we metalearn dynamics and characteristics of closed and open two-level systems, as well as the Heisenberg model. Based on experimental data of a Loss-DiVincenzo spin qubit hosted in a Ge/Si core/shell nanowire for different gate voltage configurations, we predict qubit characteristics, i.e., g factor and Rabi frequency using metalearning. The algorithm we introduce improves upon previous state-of-the-art metalearning methods for physics-based systems by introducing techniques such as adaptive learning rates and a global optimizer for improved robustness and increased computational efficiency. We benchmark our method against other metalearning methods, a vanilla transformer, and a multilayer perceptron, and demonstrate improved performance.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (36)

  1. Y. Alexeev, M. H. Farag, T. L. Patti, M. E. Wolf, N. Ares, A. Aspuru-Guzik, S. C. Benjamin, Z. Cai, Z. Chandani, F. Fedele, et al., Artificial intelligence for quantum computing, Nat. Commun. 16, 10829 (2025).
  2. M. Krenn, J. Landgraf, T. Foesel, and F. Marquardt, Artificial intelligence and machine learning for quantum technologies, Phys. Rev. A 107, 010101 (2023).
  3. V. Gebhart, R. Santagati, A. Gentile, E. Gauger, D. Craig, N. Ares, L. Banchi, F. Marquardt, L. Pezze, and C. Bonato, Learning quantum systems, Nat. Rev. Phys. 5, 141 (2023).
  4. P. Vaidhyanathan, F. Marquardt, M. T. Mitchison, and N. Ares, Quantum feedback control with a transformer neural network architecture, Phys. Rev. Res. 8, L012043 (2026).
  5. F. Marquardt, Machine learning and quantum devices, SciPost Phys. Lect. Notes, 29 (2021).
  6. D. L. Craig, H. Moon, F. Fedele, D. T. Lennon, B. van Straaten, F. Vigneau, L. C. Camenzind, D. M. Zumbühl, G. A. D. Briggs, M. A. Osborne, D. Sejdinovic, and N. Ares, Bridging the reality gap in quantum devices with physics-aware machine learning, Phys. Rev. X 14, 011001 (2024).
  7. D. L. Craig, N. Ares, and E. M. Gauger, Differentiable master equation solver for quantum device characterization, Phys. Rev. Res. 6, 043175 (2024).
  8. B. Flynn, A. A. Gentile, N. Wiebe, R. Santagati, and A. Laing, Quantum model learning agent: Characterisation of quantum systems through machine learning, New J. Phys. 24, 053034 (2022).
  9. B. van Straaten, J. Hickie, L. Schorling, J. Schuff, F. Fedele, and N. Ares, QArray: A GPU-accelerated constant capacitance model simulator for large quantum dot arrays, SciPost Phys. Codebases, 35 (2024).
  10. N. Ares, Machine learning as an enabler of qubit scalability, Nat. Rev. Mater. 6, 870 (2021).
  11. J. Schuff, M. J. Carballido, M. Kotzagiannidis, J. C. Calvo, M. Caselli, J. Rawling, D. L. Craig, B. van Straaten, B. Severin, F. Fedele, S. Svab, P. C. Kwon, R. S. Eggli, T. Patlatiuk, N. Korda, D. Zumbühl, and N. Ares, Fully autonomous tuning of a spin qubit, Nat. Electron. 9, 304 (2026).
  12. V. Nguyen, S. B. Orbell, D. T. Lennon, H. Moon, F. Vigneau, L. C. Camenzind, L. Yu, D. M. Zumbühl, G. A. D. Briggs, M. A. Osborne, D. Sejdinovic, and N. Ares, Deep reinforcement learning for efficient measurement of quantum devices, npj Quantum Inf. 7, 100 (2021).
  13. B. van Straaten, F. Fedele, F. Vigneau, J. Hickie, D. Jirovec, A. Ballabio, D. Chrastina, G. Isella, G. Katsaros, and N. Ares, All RF-based tuning algorithm for quantum devices using machine learning, Phys. Rev. Appl. 24, 054030 (2025).
  14. J. Schuff, D. T. Lennon, S. Geyer, D. L. Craig, F. Fedele, F. Vigneau, L. C. Camenzind, A. V. Kuhlmann, G. A. D. Briggs, D. M. Zumbühl, D. Sejdinovic, and N. Ares, Identifying Pauli spin blockade using deep learning, Quantum 7, 1077 (2023).
  15. J. P. Zwolak and J. M. Taylor, Colloquium: Advances in automation of quantum dot devices control, Rev. Mod. Phys. 95, 011006 (2023).
  16. E. Flurin, L. S. Martin, S. Hacohen-Gourgy, and I. Siddiqi, Using a recurrent neural network to reconstruct quantum dynamics of a superconducting qubit from physical observations, Phys. Rev. X 10, 011006 (2020).
  17. T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey, Meta-learning in neural networks: A survey, IEEE Trans. Pattern Anal. Mach. Intell. 44, 5149 (2022).
  18. S. Thrun and L. Pratt, Learning to learn: Introduction and overview, in Learning to Learn, edited by S. Thrun and L. Pratt (Springer US, Boston, MA, 1998), pp. 3–17.
  19. J. Schuff, Characterisation and fully autonomous tuning of spin qubits with machine learning, Ph.D. thesis, University of Oxford, 2024.
  20. Q. Li, T. Wang, V. Roychowdhury, and M. K. Jawed, Metalearning generalizable dynamics from trajectories, Phys. Rev. Lett. 131, 067301 (2023).
  21. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, in Advances in Neural Information Processing Systems, Vol. 30, edited by I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Curran Associates, Inc., 2017).
  22. C. Finn, P. Abbeel, and S. Levine, Model-agnostic meta-learning for fast adaptation of deep networks, in International Conference on Machine Learning (PMLR, 2017), pp. 1126–1135.
  23. A. Nichol, J. Achiam, and J. Schulman, On first-order meta-learning algorithms, arXiv:1803.02999.
  24. A. Rajeswaran, C. Finn, S. M. Kakade, and S. Levine, Meta-learning with implicit gradients, in Advances in Neural Information Processing Systems, Vol. 32 (NeurIPS, 2019).
  25. L. M. Zintgraf, K. Shiarlis, V. Kurin, K. Hofmann, and S. Whiteson, CAML: Fast context adaptation via meta-learning, arXiv:1810.03642.
  26. R. T. Chen, Y. Rubanova, J. Bettencourt, and D. K. Duvenaud, Neural ordinary differential equations, in Advances in Neural Information Processing Systems (Curran Associates, Inc., 2018), Vol. 31.
  27. P. Vaidhyanathan, A. Papatheodorou, M. T. Mitchison, N. Ares, and I. Havoutis, MetaSym: A symplectic meta-learning framework for physical intelligence, arXiv:2502.16667.
  28. J. M. Martınez, Practical quasi-Newton methods for solving nonlinear systems, J. Comput. Appl. Math. 124, 97 (2000).
  29. L. C. Melo, Transformers are meta-reinforcement learners, in International Conference on Machine Learning (PMLR, 2022), pp. 15340–15359.
  30. G. Burkard, T. D. Ladd, A. Pan, J. M. Nichol, and J. R. Petta, Semiconductor spin qubits, Rev. Mod. Phys. 95, 025003 (2023).
  31. M. J. Carballido, S. Svab, R. S. Eggli, T. Patlatiuk, P. C. Kwon, J. Schuff, R. M. Kaiser, L. C. Camenzind, A. Li, N. Ares, E. P. A. M. Bakkers, S. Bosco, J. C. Egues, D. Loss, and D. M. Zumbühl, Compromise-free scaling of qubit speed and coherence, Nat. Commun. 16, 7616 (2025).
  32. F. N. Froning, L. C. Camenzind, O. A. van der Molen, A. Li, E. P. Bakkers, D. M. Zumbühl, and F. R. Braakman, Ultrafast hole spin qubit with gate-tunable spin–orbit switch functionality, Nat. Nanotechnol. 16, 308 (2021).
  33. L. Schorling, P. Vaidhyanathan, J. Schuff, M. J. Carballido, D. Zumbühl, G. Milburn, F. Marquardt, J. Foerster, M. Osborne, and N. Ares, Code repository, GitHub, 2026, https://github.com/blueluckyluke/malgo.
  34. G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, Densely connected convolutional networks, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Washington DC, 2017), pp. 2261–2269.
  35. D. C. Liu and J. Nocedal, On the limited memory BFGS method for large scale optimization, Math. Program. 45, 503 (1989).
  36. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.

Outline

Information

Phys. Rev. Research 8, 033248– Published 31 August, 2026
  • Received 6 June 2025
  • Accepted 23 July 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