Cargando…

Power of data in quantum machine learning

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Hsin-Yuan, Broughton, Michael, Mohseni, Masoud, Babbush, Ryan, Boixo, Sergio, Neven, Hartmut, McClean, Jarrod R.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8113501/
https://www.ncbi.nlm.nih.gov/pubmed/33976136
http://dx.doi.org/10.1038/s41467-021-22539-9
_version_ 1783690873967476736
author Huang, Hsin-Yuan
Broughton, Michael
Mohseni, Masoud
Babbush, Ryan
Boixo, Sergio
Neven, Hartmut
McClean, Jarrod R.
author_facet Huang, Hsin-Yuan
Broughton, Michael
Mohseni, Masoud
Babbush, Ryan
Boixo, Sergio
Neven, Hartmut
McClean, Jarrod R.
author_sort Huang, Hsin-Yuan
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8113501
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-81135012021-05-14 Power of data in quantum machine learning Huang, Hsin-Yuan Broughton, Michael Mohseni, Masoud Babbush, Ryan Boixo, Sergio Neven, Hartmut McClean, Jarrod R. Nat Commun Article 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. Nature Publishing Group UK 2021-05-11 /pmc/articles/PMC8113501/ /pubmed/33976136 http://dx.doi.org/10.1038/s41467-021-22539-9 Text en © The Author(s) 2021 https://creativecommons.org/licenses/by/4.0/Open Access 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/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Huang, Hsin-Yuan
Broughton, Michael
Mohseni, Masoud
Babbush, Ryan
Boixo, Sergio
Neven, Hartmut
McClean, Jarrod R.
Power of data in quantum machine learning
title Power of data in quantum machine learning
title_full Power of data in quantum machine learning
title_fullStr Power of data in quantum machine learning
title_full_unstemmed Power of data in quantum machine learning
title_short Power of data in quantum machine learning
title_sort power of data in quantum machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8113501/
https://www.ncbi.nlm.nih.gov/pubmed/33976136
http://dx.doi.org/10.1038/s41467-021-22539-9
work_keys_str_mv AT huanghsinyuan powerofdatainquantummachinelearning
AT broughtonmichael powerofdatainquantummachinelearning
AT mohsenimasoud powerofdatainquantummachinelearning
AT babbushryan powerofdatainquantummachinelearning
AT boixosergio powerofdatainquantummachinelearning
AT nevenhartmut powerofdatainquantummachinelearning
AT mccleanjarrodr powerofdatainquantummachinelearning