{"id":220425,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00220425","sets":["1164:10193:10905:11012"]},"path":["11012"],"owner":"44499","recid":"220425","title":["Quantum Generative Model with Optimal Transport"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-10-20"},"_buckets":{"deposit":"d9de32d0-013b-4931-9c5c-6323f1d5ba84"},"_deposit":{"id":"220425","pid":{"type":"depid","value":"220425","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Quantum Generative Model with Optimal Transport","author_link":["576609","576610","576605","576606","576607","576608"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Quantum Generative Model with Optimal Transport"},{"subitem_title":"Quantum Generative Model with Optimal Transport","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2022-10-20","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Sony Group Corporation／Quantum Computing Center, Keio University／Graduate School of Science and Technology, Keio University"},{"subitem_text_value":"Mizuho Research & Technologies, Ltd."},{"subitem_text_value":"Quantum Computing Center, Keio University／Department of Applied Physics and Physico-Informatics, Keio University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Sony Group Corporation / Quantum Computing Center, Keio University / Graduate School of Science and Technology, Keio University","subitem_text_language":"en"},{"subitem_text_value":"Mizuho Research & Technologies, Ltd.","subitem_text_language":"en"},{"subitem_text_value":"Quantum Computing Center, Keio University / Department of Applied Physics and Physico-Informatics, Keio University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/220425/files/IPSJ-QS22007021.pdf","label":"IPSJ-QS22007021.pdf"},"date":[{"dateType":"Available","dateValue":"2024-10-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-QS22007021.pdf","filesize":[{"value":"1.6 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"53"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"83489858-3002-400c-8e98-066e882ca360","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiroyuki, Tezuka"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shumpei, Uno"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoki, Yamamoto"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiroyuki, Tezuka","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shumpei, Uno","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Naoki, Yamamoto","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12894105","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2435-6492","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Generative model is an unsupervised machine learning framework, that exhibits strong performance in imaging or anomaly detection in classical machine learning regime. Recently we find several quantum version of generative model, some of which are even proven to have quantum advantage. However, those proposals have a strict limitation; that is, the quantum state to be learned (i.e., the quantum state that the model produces) is limited to a single quantum state, and thus those methods are not applicable to a set of quantum states. In this paper, we propose a quantum generative model that can learn a set of quantum state, in an unsupervised machine learning framework. The key idea is to introduce a loss function calculated based on optimal transport distance, i.e. Wasserstein distance. We then apply the proposed method to an anomaly detection task, that cannot be handled via existing methods. The proposed model paves the way for a wide application such as the health check of quantum devices and efficient initialization of quantum computation.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Generative model is an unsupervised machine learning framework, that exhibits strong performance in imaging or anomaly detection in classical machine learning regime. Recently we find several quantum version of generative model, some of which are even proven to have quantum advantage. However, those proposals have a strict limitation; that is, the quantum state to be learned (i.e., the quantum state that the model produces) is limited to a single quantum state, and thus those methods are not applicable to a set of quantum states. In this paper, we propose a quantum generative model that can learn a set of quantum state, in an unsupervised machine learning framework. The key idea is to introduce a loss function calculated based on optimal transport distance, i.e. Wasserstein distance. We then apply the proposed method to an anomaly detection task, that cannot be handled via existing methods. The proposed model paves the way for a wide application such as the health check of quantum devices and efficient initialization of quantum computation.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"11","bibliographic_titles":[{"bibliographic_title":"研究報告量子ソフトウェア（QS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-10-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"21","bibliographicVolumeNumber":"2022-QS-7"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T14:34:35.350834+00:00","created":"2025-01-19T01:20:28.173802+00:00","links":{}}