Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unleashing the Expressive Power of Pulse-Based Quantum Neural Networks (2402.02880v2)

Published 5 Feb 2024 in quant-ph, cs.ET, and cs.LG

Abstract: Quantum machine learning (QML) based on Noisy Intermediate-Scale Quantum (NISQ) devices hinges on the optimal utilization of limited quantum resources. While gate-based QML models are user-friendly for software engineers, their expressivity is restricted by the permissible circuit depth within a finite coherence time. In contrast, pulse-based models enable the construction of "infinitely" deep quantum neural networks within the same time, which may unleash greater expressive power for complex learning tasks. In this paper, this potential is investigated from the perspective of quantum control theory. We first indicate that the nonlinearity of pulse-based models comes from the encoding process that can be viewed as the continuous limit of data-reuploading in gate-based models. Subsequently, we prove that the pulse-based model can approximate arbitrary nonlinear functions when the underlying physical system is ensemble controllable. Under this condition, numerical simulations demonstrate the enhanced expressivity by either increasing the pulse length or the number of qubits. As anticipated, we show through numerical examples that the pulse-based model can unleash more expressive power compared to the gate-based model. These findings lay a theoretical foundation for understanding and designing expressive QML models using NISQ devices.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Quantum supremacy using a programmable superconducting processor. Nature, 574(7779):505–510, 2019.
  2. Quantum computational advantage using photons. Science, 370(6523):1460–1463, 2020.
  3. Quantum computational advantage via 60-qubit 24-cycle random circuit sampling. Science bulletin, 67(3):240–245, 2022.
  4. Quantum advantage in learning from experiments. Science, 376(6598):1182–1186, 2022.
  5. Hybrid quantum-classical algorithms and quantum error mitigation. Journal of the Physical Society of Japan, 90(3):032001, 2021.
  6. Hybrid quantum-classical algorithms in the noisy intermediate-scale quantum era and beyond. Physical Review A, 106(1):010101, 2022.
  7. Classification with quantum neural networks on near term processors. arXiv preprint arXiv:1802.06002, 2018.
  8. Barren plateaus in quantum neural network training landscapes. Nature communications, 9(1):4812, 2018.
  9. End-to-end quantum machine learning implemented with controlled quantum dynamics. Physical Review Applied, 14(6):064020, 2020.
  10. Experimental quantum end-to-end learning on a superconducting processor. npj Quantum Information, 9(1):18, 2023.
  11. Variational quantum pulse learning. In 2022 IEEE International Conference on Quantum Computing and Engineering (QCE), pages 556–565. IEEE, 2022.
  12. Pulse-efficient quantum machine learning. Quantum, 7:1130, 2023.
  13. Pulse-level optimization of parameterized quantum circuits for variational quantum algorithms. arXiv preprint arXiv:2211.00350, 2022.
  14. Expressive power of parametrized quantum circuits. Physical Review Research, 2(3):033125, 2020.
  15. On the universality of the quantum approximate optimization algorithm. Quantum Information Processing, 19(9):1–26, 2020.
  16. Jacob Biamonte. Universal variational quantum computation. Physical Review A, 103(3):L030401, 2021.
  17. Universal discriminative quantum neural networks. Quantum Machine Intelligence, 3(1):1–11, 2021.
  18. Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms. Advanced Quantum Technologies, 2(12):1900070, 2019.
  19. Effect of data encoding on the expressive power of variational quantum-machine-learning models. Physical Review A, 103(3):032430, 2021.
  20. Pseudo-dimension of quantum circuits. Quantum Machine Intelligence, 2(2):14, 2020.
  21. Efficient measure for the expressivity of variational quantum algorithms. Physical Review Letters, 128(8):080506, 2022.
  22. Statistical complexity of quantum circuits. Physical Review A, 105(6):062431, 2022.
  23. The power of quantum neural networks. Nature Computational Science, 1(6):403–409, 2021.
  24. The capacity of quantum neural networks. In CLEO: Science and Innovations, pages JM4G–5. Optica Publishing Group, 2020.
  25. Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747):209–212, 2019.
  26. Quantum machine learning in feature hilbert spaces. Physical review letters, 122(4):040504, 2019.
  27. Maria Schuld. Supervised quantum machine learning models are kernel methods. arXiv preprint arXiv:2101.11020, 2021.
  28. Universal approximation property of quantum machine learning models in quantum-enhanced feature spaces. Physical Review Letters, 127(9):090506, 2021.
  29. Expressivity of quantum neural networks. Physical Review Research, 3(3):L032049, 2021.
  30. Data re-uploading for a universal quantum classifier. Quantum, 4:226, February 2020.
  31. One qubit as a universal approximant. Phys. Rev. A, 104:012405, Jul 2021.
  32. Fock state-enhanced expressivity of quantum machine learning models. EPJ Quantum Technology, 9(1):16, 2022.
  33. Seth Lloyd. Almost any quantum logic gate is universal. Phys. Rev. Lett., 75:346–349, Jul 1995.
  34. Driven quantum dynamics: Will it blend? Physical Review X, 7(4):041015, 2017.
  35. Diagnosing barren plateaus with tools from quantum optimal control. Quantum, 6:824, 2022.
  36. Notions of controllability for bilinear multilevel quantum systems. IEEE Transactions on Automatic Control, 48(8):1399–1403, 2003.
  37. Control of inhomogeneous quantum ensembles. Phys. Rev. A, 73:030302, Mar 2006.
  38. Ensemble control on lie groups. SIAM Journal on Control and Optimization, 59(5):3805–3827, 2021.
  39. Power and limitations of single-qubit native quantum neural networks. arXiv preprint arXiv:2205.07848, 2022.
  40. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  41. Optimized quantum compilation for near-term algorithms with openpulse. In 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pages 186–200. IEEE, 2020.
  42. Pulse-efficient circuit transpilation for quantum applications on cross-resonance-based hardware. Physical Review Research, 3(4):043088, 2021.
  43. Effects of dynamical decoupling and pulse-level optimizations on ibm quantum computers. IEEE Transactions on Quantum Engineering, 3:1–10, 2022.
  44. Hybrid gate-pulse model for variational quantum algorithms. arXiv preprint arXiv:2212.00661, 2022.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now