WEKO3
アイテム
経験的誤差最小化に対する帰着スキームとマルチインスタンス学習への応用
https://ipsj.ixsq.nii.ac.jp/records/218600
https://ipsj.ixsq.nii.ac.jp/records/218600d28a7571-18b1-495c-960b-f2c00d3652ca
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-MPS22138030.pdf (874.0 kB)
|
Copyright (c) 2022 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG.
|
|
| MPS:会員：¥0, DLIB:会員：¥0 | ||
| Item type | SIG Technical Reports(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2022-06-20 | |||||||||
| タイトル | ||||||||||
| タイトル | 経験的誤差最小化に対する帰着スキームとマルチインスタンス学習への応用 | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | Reduction scheme for empirical risk minimization and its applications to Multiple-Instance Learning | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_18gh | |||||||||
| 資源タイプ | technical report | |||||||||
| 著者所属 | ||||||||||
| 九州大学大学院システム情報科学研究院 情報知能工学部門／理化学研究所革新知能統合研究センター | ||||||||||
| 著者所属 | ||||||||||
| 九州大学大学院システム情報科学研究院 情報学部門 | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Kyushu University, Department of Advanced Information Technology, Faculty of Information Science and Electrical Engineering/RIKEN, Center for Advanced Intelligence Project | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Kyushu University, Department of Informatics, Faculty of Information Science and Electrical Engineering | ||||||||||
| 著者名 |
末廣, 大貴
× 末廣, 大貴
× 瀧本, 英二
|
|||||||||
| 著者名(英) |
Daiki, Suehiro Eiji Takimoto
× Daiki, Suehiro Eiji Takimoto
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | In statistical learning, many problem formulations have been proposed so far, such as multi-class learning, complementarily labeled learning, multi-label learning, multi-task learning, which provide theoretical models for various real-world tasks. Although they have been extensively studied, the relationship among them has not been fully investigated. In this work, we focus on a particular problem formulation called Multiple-Instance Learning (MIL), and show that various learning problems including all the problems mentioned above with some of new problems can be reduced to MIL with theoretically guaranteed generalization bounds, where the reductions are established under a new reduction scheme we provide as a by-product. The results imply that the MIL-reduction gives a simplified and unified framework for designing and analyzing algorithms for various learning problems. Moreover, we show that the MIL-reduction framework can be kernelized. | |||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | In statistical learning, many problem formulations have been proposed so far, such as multi-class learning, complementarily labeled learning, multi-label learning, multi-task learning, which provide theoretical models for various real-world tasks. Although they have been extensively studied, the relationship among them has not been fully investigated. In this work, we focus on a particular problem formulation called Multiple-Instance Learning (MIL), and show that various learning problems including all the problems mentioned above with some of new problems can be reduced to MIL with theoretically guaranteed generalization bounds, where the reductions are established under a new reduction scheme we provide as a by-product. The results imply that the MIL-reduction gives a simplified and unified framework for designing and analyzing algorithms for various learning problems. Moreover, we show that the MIL-reduction framework can be kernelized. | |||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AN10505667 | |||||||||
| 書誌情報 |
研究報告数理モデル化と問題解決（MPS） 巻 2022-MPS-138, 号 30, p. 1-8, 発行日 2022-06-20 |
|||||||||
| ISSN | ||||||||||
| 収録物識別子タイプ | ISSN | |||||||||
| 収録物識別子 | 2188-8833 | |||||||||
| Notice | ||||||||||
| SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. | ||||||||||
| 出版者 | ||||||||||
| 言語 | ja | |||||||||
| 出版者 | 情報処理学会 | |||||||||
