{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217630","sets":["1164:10193:10905:10906"]},"path":["10906"],"owner":"44499","recid":"217630","title":["量子特異値分解の脱量子化によるエクストリーム機械学習の高速化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-17"},"_buckets":{"deposit":"667e553a-9020-444a-b06a-0bc140bdf8d1"},"_deposit":{"id":"217630","pid":{"type":"depid","value":"217630","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"量子特異値分解の脱量子化によるエクストリーム機械学習の高速化","author_link":["564184","564183","564186","564185"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"量子特異値分解の脱量子化によるエクストリーム機械学習の高速化"}]},"item_type_id":"4","publish_date":"2022-03-17","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪大学基礎工学研究科"},{"subitem_text_value":"大阪大学基礎工学研究科"},{"subitem_text_value":"大阪大学基礎工学研究科／大阪大学量子情報・量子生命研究センター／JSTさきがけ"},{"subitem_text_value":"大阪大学基礎工学研究科／大阪大学量子情報・量子生命研究センター／理化学研究所創発物性科学研究センター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering Science, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering Science, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering Science, Osaka University / Center for Quantum Information and Quantum Biology, Institute for Open and Transdisciplinary Research Initiatives, Osaka University / JST, PRESTO","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering Science, Osaka University / Center for Quantum Information and Quantum Biology, Institute for Open and Transdisciplinary Research Initiatives, Osaka University / Center for Emergent Matter Science, RIKEN","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/217630/files/IPSJ-QS22005008.pdf","label":"IPSJ-QS22005008.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-17"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-QS22005008.pdf","filesize":[{"value":"960.1 kB"}],"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":"931767f3-5d8d-44e4-b711-903d3d826f32","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":"武田, 伊織"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高比良, 宗一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"御手洗, 光祐"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"藤井, 啓祐"}],"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":"2016 年に Kerenidis と Prakash によって量子推薦システムが提唱され，量子計算機上で O(poly(log n)) で次元 n の行列の特異値分解が可能であることが示された．さらに，2018 年に Tang によって量子インスパイアアルゴリズム [1] が提唱され，適切なサンプリングを行えば古典計算機でも同様に O(poly(log n)) で特異値分解が計算可能であることが示された．このアルゴリズムは，入力データにセグメント木構造を持たせ，行列の行と列を乱択することで行列の次元圧縮を行い，圧縮した行列を特異値分解した後，得られた特異ベクトルなどをもちいて元の行列の特異ベクトルを復元するというものである．このように，量子計算機のアルゴリズムを古典計算機でも同様の計算量で行えるようにすることを脱量子化という．これらのアルゴリズムは，低ランク近似を行なっており，行列のランクが小さい場合，良い近似を与える．本研究では，量子インスパイア特異値分解の機械学習への応用を提案し，機械学習で用いられる標準的なデータセットにおいて低ランク近似が有効であるかどうかを数値的に検証する．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"量子ソフトウェア（QS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-03-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2022-QS-5"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217630,"updated":"2025-01-19T15:26:12.416642+00:00","links":{},"created":"2025-01-19T01:18:07.177208+00:00"}