ダウンロード数: 54
このアイテムのファイル:
ファイル | 記述 | サイズ | フォーマット | |
---|---|---|---|---|
s10994-020-05927-y.pdf | 543.83 kB | Adobe PDF | 見る/開く |
完全メタデータレコード
DCフィールド | 値 | 言語 |
---|---|---|
dc.contributor.author | Wimalawarne, Kishan | en |
dc.contributor.author | Mamitsuka, Hiroshi | en |
dc.contributor.alternative | 馬見塚, 拓 | ja |
dc.date.accessioned | 2021-03-30T04:56:57Z | - |
dc.date.available | 2021-03-30T04:56:57Z | - |
dc.date.issued | 2021-03 | - |
dc.identifier.issn | 0885-6125 | - |
dc.identifier.uri | http://hdl.handle.net/2433/262422 | - |
dc.description.abstract | We investigate optimal conditions for inducing low-rankness of higher order tensors by using convex tensor norms with reshaped tensors. We propose the reshaped tensor nuclear norm as a generalized approach to reshape tensors to be regularized by using the tensor nuclear norm. Furthermore, we propose the reshaped latent tensor nuclear norm to combine multiple reshaped tensors using the tensor nuclear norm. We analyze the generalization bounds for tensor completion models regularized by the proposed norms and show that the novel reshaping norms lead to lower Rademacher complexities. Through simulation and real-data experiments, we show that our proposed methods are favorably compared to existing tensor norms consolidating our theoretical claims. | en |
dc.format.mimetype | application/pdf | - |
dc.language.iso | eng | - |
dc.publisher | Springer Nature | en |
dc.rights | This is a post-peer-review, pre-copyedit version of an article published in Machine Learning. The final authenticated version is available online at: http://dx.doi.org/10.1007/s10994-020-05927-y. | en |
dc.rights | The full-text file will be made open to the public on 3 January 2022 in accordance with publisher's 'Terms and Conditions for Self-Archiving'. | en |
dc.rights | This is not the published version. Please cite only the published version. この論文は出版社版でありません。引用の際には出版社版をご確認ご利用ください。 | en |
dc.subject | Tensor nuclear norm | en |
dc.subject | Reshaping | en |
dc.subject | CP rank | en |
dc.subject | Generalization bounds | en |
dc.title | Reshaped tensor nuclear norms for higher order tensor completion | en |
dc.type | journal article | - |
dc.type.niitype | Journal Article | - |
dc.identifier.jtitle | Machine Learning | en |
dc.identifier.volume | 110 | - |
dc.identifier.spage | 507 | - |
dc.identifier.epage | 531 | - |
dc.relation.doi | 10.1007/s10994-020-05927-y | - |
dc.textversion | author | - |
dc.address | Department of Mathematical Informatics, The University of Tokyo | en |
dc.address | Bioinformatics Center, Institute for Chemical Research, Kyoto University | en |
dcterms.accessRights | open access | - |
datacite.date.available | 2022-01-03 | - |
出現コレクション: | 学術雑誌掲載論文等 |
このリポジトリに保管されているアイテムはすべて著作権により保護されています。