Quantum machine learning of large datasets using randomized measurements

Quantum computers promise to enhance machine learning for practical applications. Quantum machine learning for real-world data has to handle extensive amounts of high-dimensional data. However, conventional methods for measuring quantum kernels are impractical for large datasets as they scale with t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-12
Hauptverfasser: Haug, Tobias, Self, Chris N, Kim, M S
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Haug, Tobias
Self, Chris N
Kim, M S
description Quantum computers promise to enhance machine learning for practical applications. Quantum machine learning for real-world data has to handle extensive amounts of high-dimensional data. However, conventional methods for measuring quantum kernels are impractical for large datasets as they scale with the square of the dataset size. Here, we measure quantum kernels using randomized measurements. The quantum computation time scales linearly with dataset size and quadratic for classical post-processing. While our method scales in general exponentially in qubit number, we gain a substantial speed-up when running on intermediate-sized quantum computers. Further, we efficiently encode high-dimensional data into quantum computers with the number of features scaling linearly with the circuit depth. The encoding is characterized by the quantum Fisher information metric and is related to the radial basis function kernel. Our approach is robust to noise via a cost-free error mitigation scheme. We demonstrate the advantages of our methods for noisy quantum computers by classifying images with the IBM quantum computer. To achieve further speedups we distribute the quantum computational tasks between different quantum computers. Our method enables benchmarking of quantum machine learning algorithms with large datasets on currently available quantum computers.
doi_str_mv 10.48550/arxiv.2108.01039
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2108_01039</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2557684891</sourcerecordid><originalsourceid>FETCH-LOGICAL-a959-de6847e1a63b346f9753c9f5eba9c6a71a914ac07b8326d4a588d20bd26759fe3</originalsourceid><addsrcrecordid>eNotj01Lw0AYhBdBsNT-AE8ueE7cz-zuUYraQkGE3sOb7Jua0mzqbiLqrzdtPQ0Mw8w8hNxxliurNXuE-N1-5YIzmzPOpLsiMyElz6wS4oYsUtozxkRhhNZyRlbvI4Rh7GgH9UcbkB4QYmjDjvYNPUDcIfUwQMIh0TGd_AjB9137i552CGmM2GEY0i25buCQcPGvc7J9ed4uV9nm7XW9fNpk4LTLPBZWGeRQyEqqonFGy9o1GitwdQGGg-MKamYqK0XhFWhrvWCVnw5r16Cck_tL7RmzPMa2g_hTnnDLM-6UeLgkjrH_HDEN5b4fY5g-lROymfat4_IPuOxYhA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2557684891</pqid></control><display><type>article</type><title>Quantum machine learning of large datasets using randomized measurements</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Haug, Tobias ; Self, Chris N ; Kim, M S</creator><creatorcontrib>Haug, Tobias ; Self, Chris N ; Kim, M S</creatorcontrib><description>Quantum computers promise to enhance machine learning for practical applications. Quantum machine learning for real-world data has to handle extensive amounts of high-dimensional data. However, conventional methods for measuring quantum kernels are impractical for large datasets as they scale with the square of the dataset size. Here, we measure quantum kernels using randomized measurements. The quantum computation time scales linearly with dataset size and quadratic for classical post-processing. While our method scales in general exponentially in qubit number, we gain a substantial speed-up when running on intermediate-sized quantum computers. Further, we efficiently encode high-dimensional data into quantum computers with the number of features scaling linearly with the circuit depth. The encoding is characterized by the quantum Fisher information metric and is related to the radial basis function kernel. Our approach is robust to noise via a cost-free error mitigation scheme. We demonstrate the advantages of our methods for noisy quantum computers by classifying images with the IBM quantum computer. To achieve further speedups we distribute the quantum computational tasks between different quantum computers. Our method enables benchmarking of quantum machine learning algorithms with large datasets on currently available quantum computers.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2108.01039</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Circuits ; Computer Science - Learning ; Computers ; Datasets ; Image classification ; Industrial applications ; Kernels ; Machine learning ; Measurement methods ; Physics - Quantum Physics ; Quantum computers ; Quantum computing ; Radial basis function ; Statistics - Machine Learning</subject><ispartof>arXiv.org, 2022-12</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,786,887,27934</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.2108.01039$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1088/2632-2153/acb0b4$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Haug, Tobias</creatorcontrib><creatorcontrib>Self, Chris N</creatorcontrib><creatorcontrib>Kim, M S</creatorcontrib><title>Quantum machine learning of large datasets using randomized measurements</title><title>arXiv.org</title><description>Quantum computers promise to enhance machine learning for practical applications. Quantum machine learning for real-world data has to handle extensive amounts of high-dimensional data. However, conventional methods for measuring quantum kernels are impractical for large datasets as they scale with the square of the dataset size. Here, we measure quantum kernels using randomized measurements. The quantum computation time scales linearly with dataset size and quadratic for classical post-processing. While our method scales in general exponentially in qubit number, we gain a substantial speed-up when running on intermediate-sized quantum computers. Further, we efficiently encode high-dimensional data into quantum computers with the number of features scaling linearly with the circuit depth. The encoding is characterized by the quantum Fisher information metric and is related to the radial basis function kernel. Our approach is robust to noise via a cost-free error mitigation scheme. We demonstrate the advantages of our methods for noisy quantum computers by classifying images with the IBM quantum computer. To achieve further speedups we distribute the quantum computational tasks between different quantum computers. Our method enables benchmarking of quantum machine learning algorithms with large datasets on currently available quantum computers.</description><subject>Circuits</subject><subject>Computer Science - Learning</subject><subject>Computers</subject><subject>Datasets</subject><subject>Image classification</subject><subject>Industrial applications</subject><subject>Kernels</subject><subject>Machine learning</subject><subject>Measurement methods</subject><subject>Physics - Quantum Physics</subject><subject>Quantum computers</subject><subject>Quantum computing</subject><subject>Radial basis function</subject><subject>Statistics - Machine Learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj01Lw0AYhBdBsNT-AE8ueE7cz-zuUYraQkGE3sOb7Jua0mzqbiLqrzdtPQ0Mw8w8hNxxliurNXuE-N1-5YIzmzPOpLsiMyElz6wS4oYsUtozxkRhhNZyRlbvI4Rh7GgH9UcbkB4QYmjDjvYNPUDcIfUwQMIh0TGd_AjB9137i552CGmM2GEY0i25buCQcPGvc7J9ed4uV9nm7XW9fNpk4LTLPBZWGeRQyEqqonFGy9o1GitwdQGGg-MKamYqK0XhFWhrvWCVnw5r16Cck_tL7RmzPMa2g_hTnnDLM-6UeLgkjrH_HDEN5b4fY5g-lROymfat4_IPuOxYhA</recordid><startdate>20221201</startdate><enddate>20221201</enddate><creator>Haug, Tobias</creator><creator>Self, Chris N</creator><creator>Kim, M S</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20221201</creationdate><title>Quantum machine learning of large datasets using randomized measurements</title><author>Haug, Tobias ; Self, Chris N ; Kim, M S</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a959-de6847e1a63b346f9753c9f5eba9c6a71a914ac07b8326d4a588d20bd26759fe3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Circuits</topic><topic>Computer Science - Learning</topic><topic>Computers</topic><topic>Datasets</topic><topic>Image classification</topic><topic>Industrial applications</topic><topic>Kernels</topic><topic>Machine learning</topic><topic>Measurement methods</topic><topic>Physics - Quantum Physics</topic><topic>Quantum computers</topic><topic>Quantum computing</topic><topic>Radial basis function</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Haug, Tobias</creatorcontrib><creatorcontrib>Self, Chris N</creatorcontrib><creatorcontrib>Kim, M S</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Haug, Tobias</au><au>Self, Chris N</au><au>Kim, M S</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Quantum machine learning of large datasets using randomized measurements</atitle><jtitle>arXiv.org</jtitle><date>2022-12-01</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Quantum computers promise to enhance machine learning for practical applications. Quantum machine learning for real-world data has to handle extensive amounts of high-dimensional data. However, conventional methods for measuring quantum kernels are impractical for large datasets as they scale with the square of the dataset size. Here, we measure quantum kernels using randomized measurements. The quantum computation time scales linearly with dataset size and quadratic for classical post-processing. While our method scales in general exponentially in qubit number, we gain a substantial speed-up when running on intermediate-sized quantum computers. Further, we efficiently encode high-dimensional data into quantum computers with the number of features scaling linearly with the circuit depth. The encoding is characterized by the quantum Fisher information metric and is related to the radial basis function kernel. Our approach is robust to noise via a cost-free error mitigation scheme. We demonstrate the advantages of our methods for noisy quantum computers by classifying images with the IBM quantum computer. To achieve further speedups we distribute the quantum computational tasks between different quantum computers. Our method enables benchmarking of quantum machine learning algorithms with large datasets on currently available quantum computers.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2108.01039</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-12
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2108_01039
source arXiv.org; Free E- Journals
subjects Circuits
Computer Science - Learning
Computers
Datasets
Image classification
Industrial applications
Kernels
Machine learning
Measurement methods
Physics - Quantum Physics
Quantum computers
Quantum computing
Radial basis function
Statistics - Machine Learning
title Quantum machine learning of large datasets using randomized measurements
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-03T06%3A53%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Quantum%20machine%20learning%20of%20large%20datasets%20using%20randomized%20measurements&rft.jtitle=arXiv.org&rft.au=Haug,%20Tobias&rft.date=2022-12-01&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2108.01039&rft_dat=%3Cproquest_arxiv%3E2557684891%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2557684891&rft_id=info:pmid/&rfr_iscdi=true