Potential and limitations of random Fourier features for dequantizing quantum machine learning
Quantum machine learning is arguably one of the most explored applications of near-term quantum devices. Much focus has been put on notions of variational quantum machine learning where parameterized quantum circuits (PQCs) are used as learning models. These PQC models have a rich structure which su...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Sweke, Ryan Recio, Erik Jerbi, Sofiene Gil-Fuster, Elies Fuller, Bryce Eisert, Jens Meyer, Johannes Jakob |
| description | Quantum machine learning is arguably one of the most explored applications of
near-term quantum devices. Much focus has been put on notions of variational
quantum machine learning where parameterized quantum circuits (PQCs) are used
as learning models. These PQC models have a rich structure which suggests that
they might be amenable to efficient dequantization via random Fourier features
(RFF). In this work, we establish necessary and sufficient conditions under
which RFF does indeed provide an efficient dequantization of variational
quantum machine learning for regression. We build on these insights to make
concrete suggestions for PQC architecture design, and to identify structures
which are necessary for a regression problem to admit a potential quantum
advantage via PQC based optimization. |
| doi_str_mv | 10.48550/arxiv.2309.11647 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2309_11647</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2309_11647</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-25c53ee673cb9dae3f5f8ce27ff002327b0027a26b213d07df4e672b4ab70ea33</originalsourceid><addsrcrecordid>eNotj0FOwzAQRb1hgQoHYMVcIMGx47hdVhUFpEqw6JpoEo-ppdgGJ0HA6TGhqzea_2ekx9hNxct6rRS_w_TlPksh-aasqqbWl-z1JU4UJocDYDAwOO8mnFwMI0QLKe-ih32ck6MElnCaE41gYwJDHzPmyx8X3mAZZw8e-5MLBANhCjm4YhcWh5Guz1yx4_7-uHssDs8PT7vtocBG60KoXkmiRsu-2xgkaZVd9yS0tZwLKXSXoVE0naik4drYOpdFV2OnOaGUK3b7_3YRbN-T85i-2z_RdhGVvyCVUEA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Potential and limitations of random Fourier features for dequantizing quantum machine learning</title><source>arXiv.org</source><creator>Sweke, Ryan ; Recio, Erik ; Jerbi, Sofiene ; Gil-Fuster, Elies ; Fuller, Bryce ; Eisert, Jens ; Meyer, Johannes Jakob</creator><creatorcontrib>Sweke, Ryan ; Recio, Erik ; Jerbi, Sofiene ; Gil-Fuster, Elies ; Fuller, Bryce ; Eisert, Jens ; Meyer, Johannes Jakob</creatorcontrib><description>Quantum machine learning is arguably one of the most explored applications of
near-term quantum devices. Much focus has been put on notions of variational
quantum machine learning where parameterized quantum circuits (PQCs) are used
as learning models. These PQC models have a rich structure which suggests that
they might be amenable to efficient dequantization via random Fourier features
(RFF). In this work, we establish necessary and sufficient conditions under
which RFF does indeed provide an efficient dequantization of variational
quantum machine learning for regression. We build on these insights to make
concrete suggestions for PQC architecture design, and to identify structures
which are necessary for a regression problem to admit a potential quantum
advantage via PQC based optimization.</description><identifier>DOI: 10.48550/arxiv.2309.11647</identifier><language>eng</language><subject>Computer Science - Learning ; Physics - Quantum Physics</subject><creationdate>2023-09</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2309.11647$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2309.11647$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Sweke, Ryan</creatorcontrib><creatorcontrib>Recio, Erik</creatorcontrib><creatorcontrib>Jerbi, Sofiene</creatorcontrib><creatorcontrib>Gil-Fuster, Elies</creatorcontrib><creatorcontrib>Fuller, Bryce</creatorcontrib><creatorcontrib>Eisert, Jens</creatorcontrib><creatorcontrib>Meyer, Johannes Jakob</creatorcontrib><title>Potential and limitations of random Fourier features for dequantizing quantum machine learning</title><description>Quantum machine learning is arguably one of the most explored applications of
near-term quantum devices. Much focus has been put on notions of variational
quantum machine learning where parameterized quantum circuits (PQCs) are used
as learning models. These PQC models have a rich structure which suggests that
they might be amenable to efficient dequantization via random Fourier features
(RFF). In this work, we establish necessary and sufficient conditions under
which RFF does indeed provide an efficient dequantization of variational
quantum machine learning for regression. We build on these insights to make
concrete suggestions for PQC architecture design, and to identify structures
which are necessary for a regression problem to admit a potential quantum
advantage via PQC based optimization.</description><subject>Computer Science - Learning</subject><subject>Physics - Quantum Physics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj0FOwzAQRb1hgQoHYMVcIMGx47hdVhUFpEqw6JpoEo-ppdgGJ0HA6TGhqzea_2ekx9hNxct6rRS_w_TlPksh-aasqqbWl-z1JU4UJocDYDAwOO8mnFwMI0QLKe-ih32ck6MElnCaE41gYwJDHzPmyx8X3mAZZw8e-5MLBANhCjm4YhcWh5Guz1yx4_7-uHssDs8PT7vtocBG60KoXkmiRsu-2xgkaZVd9yS0tZwLKXSXoVE0naik4drYOpdFV2OnOaGUK3b7_3YRbN-T85i-2z_RdhGVvyCVUEA</recordid><startdate>20230920</startdate><enddate>20230920</enddate><creator>Sweke, Ryan</creator><creator>Recio, Erik</creator><creator>Jerbi, Sofiene</creator><creator>Gil-Fuster, Elies</creator><creator>Fuller, Bryce</creator><creator>Eisert, Jens</creator><creator>Meyer, Johannes Jakob</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230920</creationdate><title>Potential and limitations of random Fourier features for dequantizing quantum machine learning</title><author>Sweke, Ryan ; Recio, Erik ; Jerbi, Sofiene ; Gil-Fuster, Elies ; Fuller, Bryce ; Eisert, Jens ; Meyer, Johannes Jakob</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-25c53ee673cb9dae3f5f8ce27ff002327b0027a26b213d07df4e672b4ab70ea33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Physics - Quantum Physics</topic><toplevel>online_resources</toplevel><creatorcontrib>Sweke, Ryan</creatorcontrib><creatorcontrib>Recio, Erik</creatorcontrib><creatorcontrib>Jerbi, Sofiene</creatorcontrib><creatorcontrib>Gil-Fuster, Elies</creatorcontrib><creatorcontrib>Fuller, Bryce</creatorcontrib><creatorcontrib>Eisert, Jens</creatorcontrib><creatorcontrib>Meyer, Johannes Jakob</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sweke, Ryan</au><au>Recio, Erik</au><au>Jerbi, Sofiene</au><au>Gil-Fuster, Elies</au><au>Fuller, Bryce</au><au>Eisert, Jens</au><au>Meyer, Johannes Jakob</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Potential and limitations of random Fourier features for dequantizing quantum machine learning</atitle><date>2023-09-20</date><risdate>2023</risdate><abstract>Quantum machine learning is arguably one of the most explored applications of
near-term quantum devices. Much focus has been put on notions of variational
quantum machine learning where parameterized quantum circuits (PQCs) are used
as learning models. These PQC models have a rich structure which suggests that
they might be amenable to efficient dequantization via random Fourier features
(RFF). In this work, we establish necessary and sufficient conditions under
which RFF does indeed provide an efficient dequantization of variational
quantum machine learning for regression. We build on these insights to make
concrete suggestions for PQC architecture design, and to identify structures
which are necessary for a regression problem to admit a potential quantum
advantage via PQC based optimization.</abstract><doi>10.48550/arxiv.2309.11647</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2309.11647 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2309_11647 |
| source | arXiv.org |
| subjects | Computer Science - Learning Physics - Quantum Physics |
| title | Potential and limitations of random Fourier features for dequantizing quantum machine learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T15%3A10%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Potential%20and%20limitations%20of%20random%20Fourier%20features%20for%20dequantizing%20quantum%20machine%20learning&rft.au=Sweke,%20Ryan&rft.date=2023-09-20&rft_id=info:doi/10.48550/arxiv.2309.11647&rft_dat=%3Carxiv_GOX%3E2309_11647%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |