Papers
Topics
Authors
Recent
Search
2000 character limit reached

Piecewise Polynomial Tensor Network Quantum Feature Encoding

Published 12 Feb 2024 in quant-ph | (2402.07671v5)

Abstract: This work introduces a novel method for embedding continuous variables into quantum circuits via piecewise polynomial features, utilizing low-rank tensor networks. Our approach, termed Piecewise Polynomial Tensor Network Quantum Feature Encoding (PPTNQFE), aims to broaden the applicability of quantum algorithms by incorporating spatially localized representations suited for numerical applications like partial differential equations and function regression. We demonstrate the potential of PPTNQFE through efficient point evaluations of solutions of discretized differential equations and in modeling functions with localized features such as jump discontinuities. While promising, challenges such as unexplored noise impact and design of trainable circuits remain. This study opens new avenues for enhancing quantum models with novel feature embeddings and leveraging TN representations for a wider array of function types in quantum machine learning.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Information-theoretic bounds on quantum advantage in machine learning. Phys. Rev. Lett., 126:190505, May 2021a. doi:10.1103/PhysRevLett.126.190505. URL https://link.aps.org/doi/10.1103/PhysRevLett.126.190505.
  2. Quantum advantage in learning from experiments. Science, 376(6598):1182–1186, 2022. doi:10.1126/science.abn7293. URL https://www.science.org/doi/abs/10.1126/science.abn7293.
  3. Evaluating the evidence for exponential quantum advantage in ground-state quantum chemistry. Nature Communications, 14(1):1952, April 2023. ISSN 2041-1723. doi:10.1038/s41467-023-37587-6. URL https://doi.org/10.1038/s41467-023-37587-6.
  4. On quantum backpropagation, information reuse, and cheating measurement collapse, 2023.
  5. Quantum algorithms and the finite element method. Phys. Rev. A, 93:032324, Mar 2016. doi:10.1103/PhysRevA.93.032324. URL https://link.aps.org/doi/10.1103/PhysRevA.93.032324.
  6. Performance study of variational quantum algorithms for solving the poisson equation on a quantum computer. Phys. Rev. Appl., 20:014054, Jul 2023. doi:10.1103/PhysRevApplied.20.014054. URL https://link.aps.org/doi/10.1103/PhysRevApplied.20.014054.
  7. A rigorous and robust quantum speed-up in supervised machine learning. Nature Physics, 17(9):1013–1017, September 2021. ISSN 1745-2481. doi:10.1038/s41567-021-01287-z. URL https://doi.org/10.1038/s41567-021-01287-z.
  8. Provable advantages of kernel-based quantum learners and quantum preprocessing based on grover’s algorithm, 2023.
  9. Advantage of quantum machine learning from general computational advantages, 2023.
  10. Is quantum advantage the right goal for quantum machine learning? PRX Quantum, 3:030101, Jul 2022. doi:10.1103/PRXQuantum.3.030101. URL https://link.aps.org/doi/10.1103/PRXQuantum.3.030101.
  11. Effect of data encoding on the expressive power of variational quantum-machine-learning models. Phys. Rev. A, 103:032430, Mar 2021. doi:10.1103/PhysRevA.103.032430. URL https://link.aps.org/doi/10.1103/PhysRevA.103.032430.
  12. An exponentially-growing family of universal quantum circuits. Machine Learning: Science and Technology, 4(3):035036, aug 2023. doi:10.1088/2632-2153/ace757. URL https://dx.doi.org/10.1088/2632-2153/ace757.
  13. Exponential data encoding for quantum supervised learning. Phys. Rev. A, 107:012422, Jan 2023. doi:10.1103/PhysRevA.107.012422. URL https://link.aps.org/doi/10.1103/PhysRevA.107.012422.
  14. The inductive bias of quantum kernels. In Advances in Neural Information Processing Systems 34 (NeurIPS 2021), pages 12661–12673. Curran Associates, Inc., December 2021. URL https://proceedings.neurips.cc/paper/2021/file/69adc1e107f7f7d035d7baf04342e1ca-Paper.pdf. *equal contribution.
  15. Power of data in quantum machine learning. Nature Communications, 12(1):2631, May 2021b. ISSN 2041-1723. doi:10.1038/s41467-021-22539-9. URL https://doi.org/10.1038/s41467-021-22539-9.
  16. Quantum machine learning beyond kernel methods. Nature Communications, 14(1):517, January 2023. ISSN 2041-1723. doi:10.1038/s41467-023-36159-y. URL https://doi.org/10.1038/s41467-023-36159-y.
  17. Does provable absence of barren plateaus imply classical simulability? Or, why we need to rethink variational quantum computing, 2023.
  18. Contextuality and inductive bias in quantum machine learning, 2023.
  19. An inductive bias from quantum mechanics: learning order effects with non-commuting measurements, 2023.
  20. Theory for equivariant quantum neural networks, 2022.
  21. Theoretical guarantees for permutation-equivariant quantum neural networks. npj Quantum Information, 10(1):12, January 2024. ISSN 2056-6387. doi:10.1038/s41534-024-00804-1. URL https://doi.org/10.1038/s41534-024-00804-1.
  22. Generalization despite overfitting in quantum machine learning models. Quantum, 7:1210, December 2023. ISSN 2521-327X. doi:10.22331/q-2023-12-20-1210. URL https://doi.org/10.22331/q-2023-12-20-1210.
  23. Quantum convolutional neural networks. Nature Physics, 15(12):1273–1278, December 2019. ISSN 1745-2481. doi:10.1038/s41567-019-0648-8. URL https://doi.org/10.1038/s41567-019-0648-8.
  24. Exploiting symmetry in variational quantum machine learning. PRX Quantum, 4:010328, Mar 2023. doi:10.1103/PRXQuantum.4.010328. URL https://link.aps.org/doi/10.1103/PRXQuantum.4.010328.
  25. What can we learn from quantum convolutional neural networks?, 2023.
  26. Geometric quantum machine learning of bqpa𝑎{}^{a}start_FLOATSUPERSCRIPT italic_a end_FLOATSUPERSCRIPT protocols and latent graph classifiers, 2024.
  27. Solving nonlinear differential equations with differentiable quantum circuits. Phys. Rev. A, 103:052416, May 2021. doi:10.1103/PhysRevA.103.052416. URL https://link.aps.org/doi/10.1103/PhysRevA.103.052416.
  28. Quantum chebyshev transform: Mapping, embedding, learning and sampling distributions, 2023.
  29. I. V. Oseledets. Constructive Representation of Functions in Low-Rank Tensor Formats. Constructive Approximation, 37(1):1–18, February 2013. ISSN 1432-0940. doi:10.1007/s00365-012-9175-x. URL https://doi.org/10.1007/s00365-012-9175-x.
  30. Approximation Theory of Tree Tensor Networks: Tensorized Univariate Functions. Constructive Approximation, 58(2):463–544, October 2023. ISSN 1432-0940. doi:10.1007/s00365-023-09620-w. URL https://doi.org/10.1007/s00365-023-09620-w.
  31. Dietrich Braess. Finite Elements: Theory, Fast Solvers, and Applications in Solid Mechanics. Cambridge University Press, 3 edition, 2007.
  32. Dmitry Yarotsky. Error bounds for approximations with deep relu networks. Neural Networks, 94:103–114, 2017. ISSN 0893-6080. doi:https://doi.org/10.1016/j.neunet.2017.07.002. URL https://www.sciencedirect.com/science/article/pii/S0893608017301545.
  33. anthony-nouy/tensap: v1.5, July 2023. URL https://doi.org/10.5281/zenodo.8130836.
  34. Tensor networks in a nutshell, 2017.
  35. Ulrich Schollwöck. The density-matrix renormalization group in the age of matrix product states. Annals of Physics, 326(1):96–192, 2011. ISSN 0003-4916. doi:https://doi.org/10.1016/j.aop.2010.09.012. URL https://www.sciencedirect.com/science/article/pii/S0003491610001752. January 2011 Special Issue.
  36. I. V. Oseledets. Tensor-train decomposition. SIAM Journal on Scientific Computing, 33(5):2295–2317, 2011. doi:10.1137/090752286. URL https://doi.org/10.1137/090752286.
  37. Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747):209–212, March 2019. ISSN 1476-4687. doi:10.1038/s41586-019-0980-2. URL https://doi.org/10.1038/s41586-019-0980-2.
  38. Shi-Ju Ran. Encoding of matrix product states into quantum circuits of one- and two-qubit gates. Phys. Rev. A, 101:032310, Mar 2020. doi:10.1103/PhysRevA.101.032310. URL https://link.aps.org/doi/10.1103/PhysRevA.101.032310.
  39. Variational quantum algorithms for nonlinear problems. Phys. Rev. A, 101:010301, Jan 2020. doi:10.1103/PhysRevA.101.010301. URL https://link.aps.org/doi/10.1103/PhysRevA.101.010301.
  40. An efficient algorithm for sparse quantum state preparation. In 2021 58th ACM/IEEE Design Automation Conference (DAC), pages 433–438, 2021. doi:10.1109/DAC18074.2021.9586240.
  41. QTT-finite-element approximation for multiscale problems I: model problems in one dimension. Advances in Computational Mathematics, 43(2):411–442, April 2017. ISSN 1572-9044. doi:10.1007/s10444-016-9491-y. URL https://doi.org/10.1007/s10444-016-9491-y.
  42. Stability of Low-Rank Tensor Representations and Structured Multilevel Preconditioning for Elliptic PDEs. Foundations of Computational Mathematics, 20(5):1175–1236, October 2020. ISSN 1615-3383. doi:10.1007/s10208-020-09446-z. URL https://doi.org/10.1007/s10208-020-09446-z.
  43. Active learning of tree tensor networks using optimal least squares. SIAM/ASA Journal on Uncertainty Quantification, 11(3):848–876, 2023. doi:10.1137/21M1415911. URL https://doi.org/10.1137/21M1415911.
  44. Quantics tensor cross interpolation for high-resolution parsimonious representations of multivariate functions. Phys. Rev. Lett., 132:056501, Jan 2024. doi:10.1103/PhysRevLett.132.056501. URL https://link.aps.org/doi/10.1103/PhysRevLett.132.056501.
  45. A. Holmes and A. Y. Matsuura. Efficient quantum circuits for accurate state preparation of smooth, differentiable functions. In 2020 IEEE International Conference on Quantum Computing and Engineering (QCE), pages 169–179, Los Alamitos, CA, USA, oct 2020. IEEE Computer Society. doi:10.1109/QCE49297.2020.00030. URL https://doi.ieeecomputersociety.org/10.1109/QCE49297.2020.00030.
  46. Quantum state preparation using tensor networks. Quantum Science and Technology, 8(3):035027, jun 2023. doi:10.1088/2058-9565/acd9e7. URL https://dx.doi.org/10.1088/2058-9565/acd9e7.
  47. A quantum-inspired approach to exploit turbulence structures. Nature Computational Science, 2(1):30–37, January 2022. ISSN 2662-8457. doi:10.1038/s43588-021-00181-1. URL https://doi.org/10.1038/s43588-021-00181-1.
  48. Extracting a function encoded in amplitudes of a quantum state by tensor network and orthogonal function expansion. Quantum Information Processing, 22(6):239, June 2023. ISSN 1573-1332. doi:10.1007/s11128-023-03937-y. URL https://doi.org/10.1007/s11128-023-03937-y.
  49. Quantum state preparation of normal distributions using matrix product states. npj Quantum Information, 10(1):15, January 2024. ISSN 2056-6387. doi:10.1038/s41534-024-00805-0. URL https://doi.org/10.1038/s41534-024-00805-0.
  50. Quantum algorithm for linear systems of equations. Phys. Rev. Lett., 103:150502, Oct 2009. doi:10.1103/PhysRevLett.103.150502. URL https://link.aps.org/doi/10.1103/PhysRevLett.103.150502.
  51. Quantum algorithm for systems of linear equations with exponentially improved dependence on precision. SIAM Journal on Computing, 46(6):1920–1950, 2017. doi:10.1137/16M1087072. URL https://doi.org/10.1137/16M1087072.
  52. Variational Quantum Linear Solver. Quantum, 7:1188, November 2023. ISSN 2521-327X. doi:10.22331/q-2023-11-22-1188. URL https://doi.org/10.22331/q-2023-11-22-1188.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Authors (2)

  1. Mazen Ali 
  2. Matthias Kabel 

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 3 tweets with 2 likes about this paper.

Sign Up for Free