Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 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

Post-variational quantum neural networks (2307.10560v2)

Published 20 Jul 2023 in quant-ph and cs.LG

Abstract: Hybrid quantum-classical computing in the noisy intermediate-scale quantum (NISQ) era with variational algorithms can exhibit barren plateau issues, causing difficult convergence of gradient-based optimization techniques. In this paper, we discuss "post-variational strategies", which shift tunable parameters from the quantum computer to the classical computer, opting for ensemble strategies when optimizing quantum models. We discuss various strategies and design principles for constructing individual quantum circuits, where the resulting ensembles can be optimized with convex programming. Further, we discuss architectural designs of post-variational quantum neural networks and analyze the propagation of estimation errors throughout such neural networks. Finally, we show that empirically, post-variational quantum neural networks using our architectural designs can potentially provide better results than variational algorithms and performance comparable to that of two-layer neural networks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. E. Farhi, J. Goldstone, and S. Gutmann, A quantum approximate optimization algorithm (2014), arXiv:1411.4028 [quant-ph] .
  2. E. Farhi and H. Neven, Classification with quantum neural networks on near term processors (2018), arXiv:1802.06002 [quant-ph] .
  3. M. Schuld and N. Killoran, Quantum machine learning in feature Hilbert spaces, Phys. Rev. Lett. 122, 040504 (2019).
  4. J. Preskill, Quantum Computing in the NISQ era and beyond, Quantum 2, 79 (2018).
  5. C. Ortiz Marrero, M. Kieferová, and N. Wiebe, Entanglement-induced barren plateaus, PRX Quantum 2, 040316 (2021).
  6. T. Volkoff and P. J. Coles, Large gradients via correlation in random parameterized quantum circuits, Quantum Science and Technology 6, 025008 (2021).
  7. I. Cong, S. Choi, and M. D. Lukin, Quantum convolutional neural networks, Nature Physics 15, 1273 (2019).
  8. H.-Y. Huang, K. Bharti, and P. Rebentrost, Near-term quantum algorithms for linear systems of equations with regression loss functions, New Journal of Physics 23, 113021 (2021a).
  9. K. Bharti, Quantum assisted eigensolver (2020), arXiv:2009.11001 [quant-ph] .
  10. K. Bharti and T. Haug, Iterative quantum-assisted eigensolver, Phys. Rev. A 104, L050401 (2021a).
  11. K. Bharti and T. Haug, Quantum-assisted simulator, Phys. Rev. A 104, 042418 (2021b).
  12. T. Haug and K. Bharti, Generalized quantum assisted simulator, Quantum Science and Technology 7, 045019 (2022).
  13. S. Boyd and L. Vandenberghe, Convex Optimization (Cambridge University Press, 2004).
  14. 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).
  15. J. Jäger and R. V. Krems, Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines, Nature Communications 14 (2023).
  16. H.-Y. Huang, R. Kueng, and J. Preskill, Predicting many properties of a quantum system from very few measurements, Nature Physics 16, 1050 (2020).
  17. D. Gottesman, Stabilizer Codes and Quantum Error Correction, Ph.D. thesis, Caltech (1997), arXiv:quant-ph/9705052 [quant-ph] .
  18. A. S. Nemirovsky and D. B. Yudin, Problem complexity and method efficiency in optimization (Wiley, 1983).
  19. A. M. Childs and N. Wiebe, Hamiltonian simulation using linear combinations of unitary operations, Quantum Info. Comput. 12, 901–924 (2012).
  20. K. Hornik, M. Stinchcombe, and H. White, Multilayer feedforward networks are universal approximators, Neural Networks 2, 359 (1989).
  21. F. J. Schreiber, J. Eisert, and J. J. Meyer, Classical surrogates for quantum learning models, Phys. Rev. Lett. 131, 100803 (2023).
  22. F. J. Gil Vidal and D. O. Theis, Input redundancy for parameterized quantum circuits, Frontiers in Physics 8 (2020).
  23. P. Huembeli and A. Dauphin, Characterizing the loss landscape of variational quantum circuits, Quantum Science and Technology 6, 025011 (2021).
  24. A. Mari, T. R. Bromley, and N. Killoran, Estimating the gradient and higher-order derivatives on quantum hardware, Phys. Rev. A 103, 012405 (2021).
  25. G. E. Crooks, Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition (2019), arXiv:1905.13311 [quant-ph] .
  26. H.-Y. Huang, S. Chen, and J. Preskill, Learning to predict arbitrary quantum processes, PRX Quantum 4, 040337 (2023).
  27. Y. Cao, G. G. Guerreschi, and A. Aspuru-Guzik, Quantum neuron: an elementary building block for machine learning on quantum computers (2017), arXiv:1711.11240 [quant-ph] .
  28. W. Hoeffding, Probability inequalities for sums of bounded random variables, Journal of the American Statistical Association 58, 13 (1963).
  29. G. Boole, The Mathematical Analysis of Logic (Cambridge University Press, 2009).
  30. H. Xiao, K. Rasul, and R. Vollgraf, Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017), arXiv:1708.07747 [cs.LG] .
  31. I. Kerenidis, J. Landman, and A. Prakash, Quantum algorithms for deep convolutional neural networks, in International Conference on Learning Representations (2020).
  32. Y. LeCun, C. Cortes, and C. J. Burges, The MNIST database (1998).
  33. IBM Research and Qiskit Community, Qiskit: An open-source framework for quantum computing (2017).
  34. M. J. Bremner, A. Montanaro, and D. J. Shepherd, Average-case complexity versus approximate simulation of commuting quantum computations, Phys. Rev. Lett. 117, 080501 (2016).
  35. M. J. Bremner, A. Montanaro, and D. J. Shepherd, Achieving quantum supremacy with sparse and noisy commuting quantum computations, Quantum 1, 8 (2017).
  36. M. V. Altaisky, Quantum neural network (2001), arXiv:quant-ph/0107012 [quant-ph] .
  37. M. Schuld, I. Sinayskiy, and F. Petruccione, The quest for a quantum neural network, Quantum Information Processing 13, 2567–2586 (2014).
  38. N. Wiebe, A. Kapoor, and K. M. Svore, Quantum deep learning (2015), arXiv:1412.3489 [quant-ph] .
  39. M. Schuld, I. Sinayskiy, and F. Petruccione, Simulating a perceptron on a quantum computer, Physics Letters A 379, 660–663 (2015).
  40. G. H. Low and I. L. Chuang, Optimal Hamiltonian simulation by quantum signal processing, Phys. Rev. Lett. 118, 010501 (2017).
  41. G. H. Low and I. L. Chuang, Hamiltonian simulation by qubitization, Quantum 3, 163 (2019).
  42. N. Guo, K. Mitarai, and K. Fujii, Nonlinear transformation of complex amplitudes via quantum singular value transformation (2021), arXiv:2107.10764 [quant-ph] .
  43. M. H. Stone, Linear transformations in Hilbert space, in Proceedings of the National Academy of Sciences, Vol. 16-2 (1930) pp. 172–175.
  44. M. H. Stone, On one-parameter unitary groups in Hilbert space, Annals of Mathematics 33, 643 (1932).
  45. J. E. Campbell, On a law of combination of operators (second paper), in Proceedings of the London Mathematical Society, Vol. s1-29-1 (Wiley, 1897) pp. 14–32.
  46. M.-C. Yue and A. M.-C. So, A perturbation inequality for concave functions of singular values and its applications in low-rank matrix recovery, Applied and Computational Harmonic Analysis 40, 396 (2016).
  47. P.-Å. Wedin, Perturbation theory for pseudo-inverses, BIT Numerical Mathematics 13, 217 (1973).
Citations (1)
View on Semantic Scholar

Summary

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

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