Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published May 11, 2021 | Published + Supplemental Material
Journal Article Open

Power of data in quantum machine learning

Abstract

The use of quantum computing for machine learning is among the most exciting prospective applications of quantum technologies. However, machine learning tasks where data is provided can be considerably different than commonly studied computational tasks. In this work, we show that some problems that are classically hard to compute can be easily predicted by classical machines learning from data. Using rigorous prediction error bounds as a foundation, we develop a methodology for assessing potential quantum advantage in learning tasks. The bounds are tight asymptotically and empirically predictive for a wide range of learning models. These constructions explain numerical results showing that with the help of data, classical machine learning models can be competitive with quantum models even if they are tailored to quantum problems. We then propose a projected quantum model that provides a simple and rigorous quantum speed-up for a learning problem in the fault-tolerant regime. For near-term implementations, we demonstrate a significant prediction advantage over some classical models on engineered data sets designed to demonstrate a maximal quantum advantage in one of the largest numerical tests for gate-based quantum machine learning to date, up to 30 qubits.

Additional Information

© The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. Received 18 November 2020; Accepted 16 March 2021; Published 11 May 2021. We want to thank Richard Kueng, John Platt, John Preskill, Thomas Vidick, Nathan Wiebe, and Chun-Ju Wu for valuable inputs and inspiring discussions. We thank Bálint Pató for crucial contributions in setting up simulations. Data availability: All other data that support the plots within this paper and other findings of this study are available upon reasonable request. Source data are provided with this paper. Code availability: A tutorial for reproducing smaller numerical experiments is available at https://www.tensorflow.org/quantum/tutorials/quantum_data. Author Contributions: H.H. and J.M. developed the theoretical aspects of this work. H.H. and M.B. conducted the numerical experiments and wrote the open source code. H.H., M.M., R.B., S.B., H.N., and J.M. contributed to technical discussions and writing of the manuscript. The authors declare no competing interests. Peer review information: Nature Communications thanks Nana Liu and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Attached Files

Published - s41467-021-22539-9.pdf

Supplemental Material - 41467_2021_22539_MOESM1_ESM.pdf

Supplemental Material - 41467_2021_22539_MOESM2_ESM.xlsx

Files

41467_2021_22539_MOESM1_ESM.pdf
Files (4.9 MB)
Name Size Download all
md5:f76e1186a4ef203bad78e39d9f56356d
2.9 MB Preview Download
md5:bfedbb6aabe28a26d8c575194ddd2e42
56.7 kB Download
md5:46d4e5f826770041682606bb0590917d
1.9 MB Preview Download

Additional details

Created:
August 22, 2023
Modified:
October 23, 2023