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

Let Quantum Neural Networks Choose Their Own Frequencies (2309.03279v2)

Published 6 Sep 2023 in quant-ph and cs.LG

Abstract: Parameterized quantum circuits as machine learning models are typically well described by their representation as a partial Fourier series of the input features, with frequencies uniquely determined by the feature map's generator Hamiltonians. Ordinarily, these data-encoding generators are chosen in advance, fixing the space of functions that can be represented. In this work we consider a generalization of quantum models to include a set of trainable parameters in the generator, leading to a trainable frequency (TF) quantum model. We numerically demonstrate how TF models can learn generators with desirable properties for solving the task at hand, including non-regularly spaced frequencies in their spectra and flexible spectral richness. Finally, we showcase the real-world effectiveness of our approach, demonstrating an improved accuracy in solving the Navier-Stokes equations using a TF model with only a single parameter added to each encoding operation. Since TF models encompass conventional fixed frequency models, they may offer a sensible default choice for variational quantum machine learning.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Aram W Harrow, Avinatan Hassidim,  and Seth Lloyd, “Quantum algorithm for linear systems of equations,” Physical review letters 103, 150502 (2009).
  2. Niklas Pirnay, Ryan Sweke, Jens Eisert,  and Jean-Pierre Seifert, “A super-polynomial quantum-classical separation for density modelling,” arXiv preprint arXiv:2210.14936  (2022).
  3. Yunchao Liu, Srinivasan Arunachalam,  and Kristan Temme, “A rigorous and robust quantum speed-up in supervised machine learning,” Nature Physics 17, 1013–1017 (2021a).
  4. Seth Lloyd, Silvano Garnerone,  and Paolo Zanardi, “Quantum algorithms for topological and geometric analysis of data,” Nature communications 7, 10138 (2016).
  5. Marcello Benedetti, Erika Lloyd, Stefan Sack,  and Mattia Fiorentini, “Parameterized quantum circuits as machine learning models,” Quantum Science and Technology 4, 043001 (2019).
  6. Kosuke Mitarai, Makoto Negoro, Masahiro Kitagawa,  and Keisuke Fujii, “Quantum circuit learning,” Physical Review A 98, 032309 (2018).
  7. Edward Farhi and Hartmut Neven, “Classification with quantum neural networks on near term processors,” arXiv preprint arXiv:1802.06002  (2018).
  8. Vojtěch Havlíček, Antonio D. Córcoles, Kristan Temme, Aram W. Harrow, Abhinav Kandala, Jerry M. Chow,  and Jay M. Gambetta, “Supervised learning with quantum-enhanced feature spaces,” Nature 567, 209–212 (2019).
  9. Johannes S Otterbach, Riccardo Manenti, Nasser Alidoust, A Bestwick, M Block, B Bloom, S Caldwell, N Didier, E Schuyler Fried, S Hong, et al., “Unsupervised machine learning on a hybrid quantum computer,” arXiv preprint arXiv:1712.05771  (2017).
  10. Johannes Bausch, “Recurrent quantum neural networks,” Advances in neural information processing systems 33, 1368–1379 (2020).
  11. Wen Guan, Gabriel Perdue, Arthur Pesah, Maria Schuld, Koji Terashi, Sofia Vallecorsa,  and Jean-Roch Vlimant, “Quantum machine learning in high energy physics,” Machine Learning: Science and Technology 2, 011003 (2021).
  12. Niklas Heim, Atiyo Ghosh, Oleksandr Kyriienko,  and Vincent E Elfving, “Quantum model-discovery,” arXiv preprint arXiv:2111.06376  (2021).
  13. Oleksandr Kyriienko, Annie E Paine,  and Vincent E Elfving, “Protocols for trainable and differentiable quantum generative modelling,” arXiv preprint arXiv:2202.08253  (2022).
  14. Maria Schuld, Ryan Sweke,  and Johannes Jakob Meyer, “Effect of data encoding on the expressive power of variational quantum-machine-learning models,” Physical Review A 103, 032430 (2021).
  15. Dirk Heimann, Gunnar Schönhoff,  and Frank Kirchner, “Learning capability of parametrized quantum circuits,” arXiv preprint arXiv:2209.10345  (2022).
  16. Evan Peters and Maria Schuld, “Generalization despite overfitting in quantum machine learning models,” arXiv preprint arXiv:2209.05523  (2022).
  17. Oleksandr Kyriienko and Vincent E Elfving, “Generalized quantum circuit differentiation rules,” Physical Review A 104, 052417 (2021).
  18. Oleksandr Kyriienko, Annie E Paine,  and Vincent E Elfving, “Solving nonlinear differential equations with differentiable quantum circuits,” Physical Review A 103, 052416 (2021).
  19. Alexandr Sedykh, Maninadh Podapaka, Asel Sagingalieva, Nikita Smertyak, Karan Pinto, Markus Pflitsch,  and Alexey Melnikov, “Quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes,” arXiv preprint arXiv:2304.11247  (2023).
  20. Francisco Javier Gil Vidal and Dirk Oliver Theis, “Input redundancy for parameterized quantum circuits,” Frontiers in Physics 8, 297 (2020).
  21. Andrew W. Lei, Comparisons of input encodings for quantum neural networks, Master’s thesis, University of Tartu (2020).
  22. Adrián Pérez-Salinas, Alba Cervera-Lierta, Elies Gil-Fuster,  and José I Latorre, “Data re-uploading for a universal quantum classifier,” Quantum 4, 226 (2020).
  23. Emmanuel Ovalle-Magallanes, Dora E Alvarado-Carrillo, Juan Gabriel Avina-Cervantes, Ivan Cruz-Aceves,  and Jose Ruiz-Pinales, “Quantum angle encoding with learnable rotation applied to quantum–classical convolutional neural networks,” Applied Soft Computing 141, 110307 (2023).
  24. Louis-Paul Henry, Slimane Thabet, Constantin Dalyac,  and Loïc Henriet, “Quantum evolution kernel: Machine learning on graphs with programmable arrays of qubits,” Phys. Rev. A 104, 032416 (2021).
  25. Annie E. Paine, Vincent E. Elfving,  and Oleksandr Kyriienko, “Quantum kernel methods for solving regression problems and differential equations,” Phys. Rev. A 107, 032428 (2023).
  26. Manuel John, Julian Schuhmacher, Panagiotis Barkoutsos, Ivano Tavernelli,  and Francesco Tacchino, “Optimizing quantum classification algorithms on classical benchmark datasets,” Entropy 25, 860 (2023).
  27. Gian Gentinetta, David Sutter, Christa Zoufal, Bryce Fuller,  and Stefan Woerner, “Quantum kernel alignment with stochastic gradient descent,” arXiv preprint arXiv:2304.09899  (2023).
  28. Adrian Parra-Rodriguez, Pavel Lougovski, Lucas Lamata, Enrique Solano,  and Mikel Sanz, “Digital-analog quantum computation,” Phys. Rev. A 101, 022305 (2020).
  29. Liangliang Fan and Haozhen Situ, “Compact data encoding for data re-uploading quantum classifier,” Quantum Information Processing 21, 87 (2022).
  30. Gavin E Crooks, “Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition,” arXiv preprint arXiv:1905.13311  (2019).
  31. Jonas Kübler, Simon Buchholz,  and Bernhard Schölkopf, “The inductive bias of quantum kernels,” Advances in Neural Information Processing Systems 34, 12661–12673 (2021).
  32. Atiyo Ghosh, Antonio A Gentile, Mario Dagrada, Chul Lee, Seong-hyok Kim, Hyukgeun Cha, Yunjun Choi, Brad Kim, Jeong-il Kye,  and Vincent E Elfving, “Harmonic (quantum) neural networks,” arXiv preprint arXiv:2212.07462  (2022).
  33. Andrea Skolik, Sofiene Jerbi,  and Vedran Dunjko, “Quantum agents in the gym: a variational quantum algorithm for deep q-learning,” Quantum 6, 720 (2022).
  34. Thomas Hubregtsen, David Wierichs, Elies Gil-Fuster, Peter-Jan HS Derks, Paul K Faehrmann,  and Johannes Jakob Meyer, “Training quantum embedding kernels on near-term quantum computers,” Physical Review A 106, 042431 (2022a).
  35. Sofiene Jerbi, Lukas J Fiderer, Hendrik Poulsen Nautrup, Jonas M Kübler, Hans J Briegel,  and Vedran Dunjko, “Quantum machine learning beyond kernel methods,” Nature Communications 14, 517 (2023).
  36. Johannes Jakob Meyer, Marian Mularski, Elies Gil-Fuster, Antonio Anna Mele, Francesco Arzani, Alissa Wilms,  and Jens Eisert, “Exploiting symmetry in variational quantum machine learning,” PRX Quantum 4, 010328 (2023).
  37. Ryan LaRose and Brian Coyle, “Robust data encodings for quantum classifiers,” Physical Review A 102, 032420 (2020).
  38. Maziar Raissi, Paris Perdikaris,  and George Em Karniadakis, “Physics informed deep learning (part ii): Data-driven discovery of nonlinear partial differential equations,” arXiv preprint arXiv:1711.10566  (2017).
  39. Chengping Rao, Hao Sun,  and Yang Liu, “Physics-informed deep learning for incompressible laminar flows,” Theoretical and Applied Mechanics Letters 10, 207–212 (2020).
  40. Shengfeng Xu, Zhenxu Sun, Renfang Huang, Dilong Guo, Guowei Yang,  and Shengjun Ju, “A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network,” Acta Mechanica Sinica 39, 322302 (2023).
  41. Chris D Cantwell, David Moxey, Andrew Comerford, Alessandro Bolis, Gabriele Rocco, Gianmarco Mengaldo, Daniele De Grazia, Sergey Yakovlev, J-E Lombard, Dirk Ekelschot, et al., “Nektar++: An open-source spectral/hp element framework,” Computer physics communications 192, 205–219 (2015).
  42. George Karniadakis and Spencer Sherwin, Spectral/hp element methods for computational fluid dynamics (Numerical Mathematics and Scie, 2013).
  43. Ben Jaderberg, Lewis W Anderson, Weidi Xie, Samuel Albanie, Martin Kiffner,  and Dieter Jaksch, “Quantum self-supervised learning,” Quantum Science and Technology 7, 035005 (2022).
  44. Andrea Mari, Thomas R Bromley, Josh Izaac, Maria Schuld,  and Nathan Killoran, “Transfer learning in hybrid classical-quantum neural networks,” Quantum 4, 340 (2020).
  45. Junhua Liu, Kwan Hui Lim, Kristin L Wood, Wei Huang, Chu Guo,  and He-Liang Huang, “Hybrid quantum-classical convolutional neural networks,” Science China Physics, Mechanics & Astronomy 64, 290311 (2021b).
  46. Junyu Liu, Francesco Tacchino, Jennifer R Glick, Liang Jiang,  and Antonio Mezzacapo, “Representation learning via quantum neural tangent kernels,” PRX Quantum 3, 030323 (2022).
  47. Tak Hur, Israel F Araujo,  and Daniel K Park, “Neural quantum embedding: Pushing the limits of quantum supervised learning,” arXiv preprint arXiv:2311.11412  (2023).
  48. Thomas Hubregtsen, Frederik Wilde, Shozab Qasim,  and Jens Eisert, “Single-component gradient rules for variational quantum algorithms,” Quantum Science and Technology 7, 035008 (2022b).
  49. Abhinav Kandala, Antonio Mezzacapo, Kristan Temme, Maika Takita, Markus Brink, Jerry M Chow,  and Jay M Gambetta, “Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets,” nature 549, 242–246 (2017).
  50. Marco Cerezo, Akira Sone, Tyler Volkoff, Lukasz Cincio,  and Patrick J Coles, “Cost function dependent barren plateaus in shallow parametrized quantum circuits,” Nature communications 12, 1791 (2021).
  51. Xuchen You, Shouvanik Chakrabarti,  and Xiaodi Wu, “A convergence theory for over-parameterized variational quantum eigensolvers,” arXiv preprint arXiv:2205.12481  (2022).
Citations (12)
View on Semantic Scholar

Summary

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

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