Analysis and synthesis of feature map for kernel-based quantum classifier

A method for analyzing the feature map for the kernel-based quantum classifier is developed; that is, we give a general formula for computing a lower bound of the exact training accuracy, which helps us to see whether the selected feature map is suitable for linearly separating the dataset. We show...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-08
Main Authors: Suzuki, Yudai, Yano, Hiroshi, Gao, Qi, Uno, Shumpei, Tanaka, Tomoki, Akiyama, Manato, Yamamoto, Naoki
Format: Article
Language:English
Subjects:
Classifiers
Datasets
Decomposition
Feature maps
Lower bounds
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Suzuki, Yudai
Yano, Hiroshi
Gao, Qi
Uno, Shumpei
Tanaka, Tomoki
Akiyama, Manato
Yamamoto, Naoki
description A method for analyzing the feature map for the kernel-based quantum classifier is developed; that is, we give a general formula for computing a lower bound of the exact training accuracy, which helps us to see whether the selected feature map is suitable for linearly separating the dataset. We show a proof of concept demonstration of this method for a class of 2-qubit classifier, with several 2-dimensional dataset. Also, a synthesis method, that combines different kernels to construct a better-performing feature map in a lager feature space, is presented.
doi_str_mv 10.48550/arxiv.1906.10467
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2247259251</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2247259251</sourcerecordid><originalsourceid>FETCH-LOGICAL-a521-a27496308824f6ec2ba1cd2791bcd54979fb987f41b6cbc1e555bba3be58ac3a3</originalsourceid><addsrcrecordid>eNotj8tKAzEUQIMgWGo_wF3A9dTk5jHJshQfhYKb7stN5ganTmfaZEbs31vR1eFsDhzGHqRYameMeML83X4tpRd2KYW29Q2bgVKychrgji1KOQghwNZgjJqxzarH7lLawrFveLn04wf92pB4IhynTPyIJ56GzD8p99RVAQs1_DxhP05HHjsspU0t5Xt2m7ArtPjnnO1ennfrt2r7_rpZr7YVGpAVQq29VcI50MlShIAyNlB7GWJjtK99Ct7VSctgY4iSjDEhoApkHEaFas4e_7KnPJwnKuP-MEz5OlH2APp65cFI9QPRsU7X</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2247259251</pqid></control><display><type>article</type><title>Analysis and synthesis of feature map for kernel-based quantum classifier</title><source>Publicly Available Content Database</source><creator>Suzuki, Yudai ; Yano, Hiroshi ; Gao, Qi ; Uno, Shumpei ; Tanaka, Tomoki ; Akiyama, Manato ; Yamamoto, Naoki</creator><creatorcontrib>Suzuki, Yudai ; Yano, Hiroshi ; Gao, Qi ; Uno, Shumpei ; Tanaka, Tomoki ; Akiyama, Manato ; Yamamoto, Naoki</creatorcontrib><description>A method for analyzing the feature map for the kernel-based quantum classifier is developed; that is, we give a general formula for computing a lower bound of the exact training accuracy, which helps us to see whether the selected feature map is suitable for linearly separating the dataset. We show a proof of concept demonstration of this method for a class of 2-qubit classifier, with several 2-dimensional dataset. Also, a synthesis method, that combines different kernels to construct a better-performing feature map in a lager feature space, is presented.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1906.10467</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Classifiers ; Datasets ; Decomposition ; Feature maps ; Lower bounds</subject><ispartof>arXiv.org, 2020-08</ispartof><rights>2020. 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><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2247259251?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,27925,37012,44590</link.rule.ids></links><search><creatorcontrib>Suzuki, Yudai</creatorcontrib><creatorcontrib>Yano, Hiroshi</creatorcontrib><creatorcontrib>Gao, Qi</creatorcontrib><creatorcontrib>Uno, Shumpei</creatorcontrib><creatorcontrib>Tanaka, Tomoki</creatorcontrib><creatorcontrib>Akiyama, Manato</creatorcontrib><creatorcontrib>Yamamoto, Naoki</creatorcontrib><title>Analysis and synthesis of feature map for kernel-based quantum classifier</title><title>arXiv.org</title><description>A method for analyzing the feature map for the kernel-based quantum classifier is developed; that is, we give a general formula for computing a lower bound of the exact training accuracy, which helps us to see whether the selected feature map is suitable for linearly separating the dataset. We show a proof of concept demonstration of this method for a class of 2-qubit classifier, with several 2-dimensional dataset. Also, a synthesis method, that combines different kernels to construct a better-performing feature map in a lager feature space, is presented.</description><subject>Classifiers</subject><subject>Datasets</subject><subject>Decomposition</subject><subject>Feature maps</subject><subject>Lower bounds</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNotj8tKAzEUQIMgWGo_wF3A9dTk5jHJshQfhYKb7stN5ganTmfaZEbs31vR1eFsDhzGHqRYameMeML83X4tpRd2KYW29Q2bgVKychrgji1KOQghwNZgjJqxzarH7lLawrFveLn04wf92pB4IhynTPyIJ56GzD8p99RVAQs1_DxhP05HHjsspU0t5Xt2m7ArtPjnnO1ennfrt2r7_rpZr7YVGpAVQq29VcI50MlShIAyNlB7GWJjtK99Ct7VSctgY4iSjDEhoApkHEaFas4e_7KnPJwnKuP-MEz5OlH2APp65cFI9QPRsU7X</recordid><startdate>20200817</startdate><enddate>20200817</enddate><creator>Suzuki, Yudai</creator><creator>Yano, Hiroshi</creator><creator>Gao, Qi</creator><creator>Uno, Shumpei</creator><creator>Tanaka, Tomoki</creator><creator>Akiyama, Manato</creator><creator>Yamamoto, Naoki</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></search><sort><creationdate>20200817</creationdate><title>Analysis and synthesis of feature map for kernel-based quantum classifier</title><author>Suzuki, Yudai ; Yano, Hiroshi ; Gao, Qi ; Uno, Shumpei ; Tanaka, Tomoki ; Akiyama, Manato ; Yamamoto, Naoki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a521-a27496308824f6ec2ba1cd2791bcd54979fb987f41b6cbc1e555bba3be58ac3a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Classifiers</topic><topic>Datasets</topic><topic>Decomposition</topic><topic>Feature maps</topic><topic>Lower bounds</topic><toplevel>online_resources</toplevel><creatorcontrib>Suzuki, Yudai</creatorcontrib><creatorcontrib>Yano, Hiroshi</creatorcontrib><creatorcontrib>Gao, Qi</creatorcontrib><creatorcontrib>Uno, Shumpei</creatorcontrib><creatorcontrib>Tanaka, Tomoki</creatorcontrib><creatorcontrib>Akiyama, Manato</creatorcontrib><creatorcontrib>Yamamoto, Naoki</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</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 (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest Engineering Database</collection><collection>Publicly Available Content Database</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><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Suzuki, Yudai</au><au>Yano, Hiroshi</au><au>Gao, Qi</au><au>Uno, Shumpei</au><au>Tanaka, Tomoki</au><au>Akiyama, Manato</au><au>Yamamoto, Naoki</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Analysis and synthesis of feature map for kernel-based quantum classifier</atitle><jtitle>arXiv.org</jtitle><date>2020-08-17</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>A method for analyzing the feature map for the kernel-based quantum classifier is developed; that is, we give a general formula for computing a lower bound of the exact training accuracy, which helps us to see whether the selected feature map is suitable for linearly separating the dataset. We show a proof of concept demonstration of this method for a class of 2-qubit classifier, with several 2-dimensional dataset. Also, a synthesis method, that combines different kernels to construct a better-performing feature map in a lager feature space, is presented.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1906.10467</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2247259251
source Publicly Available Content Database
subjects Classifiers
Datasets
Decomposition
Feature maps
Lower bounds
title Analysis and synthesis of feature map for kernel-based quantum classifier
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T01%3A51%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Analysis%20and%20synthesis%20of%20feature%20map%20for%20kernel-based%20quantum%20classifier&rft.jtitle=arXiv.org&rft.au=Suzuki,%20Yudai&rft.date=2020-08-17&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1906.10467&rft_dat=%3Cproquest%3E2247259251%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a521-a27496308824f6ec2ba1cd2791bcd54979fb987f41b6cbc1e555bba3be58ac3a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2247259251&rft_id=info:pmid/&rfr_iscdi=true