Distributionally Robust Safe Screening
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914770117984256 |
|---|---|
| author | Hanada, Hiroyuki Akahane, Satoshi Aoyama, Tatsuya Tanaka, Tomonari Okura, Yoshito Inatsu, Yu Hashimoto, Noriaki Murayama, Taro Hanju, Lee Kojima, Shinya Takeuchi, Ichiro |
| author_facet | Hanada, Hiroyuki Akahane, Satoshi Aoyama, Tatsuya Tanaka, Tomonari Okura, Yoshito Inatsu, Yu Hashimoto, Noriaki Murayama, Taro Hanju, Lee Kojima, Shinya Takeuchi, Ichiro |
| contents | In this study, we propose a method Distributionally Robust Safe Screening (DRSS), for identifying unnecessary samples and features within a DR covariate shift setting. This method effectively combines DR learning, a paradigm aimed at enhancing model robustness against variations in data distribution, with safe screening (SS), a sparse optimization technique designed to identify irrelevant samples and features prior to model training. The core concept of the DRSS method involves reformulating the DR covariate-shift problem as a weighted empirical risk minimization problem, where the weights are subject to uncertainty within a predetermined range. By extending the SS technique to accommodate this weight uncertainty, the DRSS method is capable of reliably identifying unnecessary samples and features under any future distribution within a specified range. We provide a theoretical guarantee of the DRSS method and validate its performance through numerical experiments on both synthetic and real-world datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16328 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Distributionally Robust Safe Screening Hanada, Hiroyuki Akahane, Satoshi Aoyama, Tatsuya Tanaka, Tomonari Okura, Yoshito Inatsu, Yu Hashimoto, Noriaki Murayama, Taro Hanju, Lee Kojima, Shinya Takeuchi, Ichiro Machine Learning In this study, we propose a method Distributionally Robust Safe Screening (DRSS), for identifying unnecessary samples and features within a DR covariate shift setting. This method effectively combines DR learning, a paradigm aimed at enhancing model robustness against variations in data distribution, with safe screening (SS), a sparse optimization technique designed to identify irrelevant samples and features prior to model training. The core concept of the DRSS method involves reformulating the DR covariate-shift problem as a weighted empirical risk minimization problem, where the weights are subject to uncertainty within a predetermined range. By extending the SS technique to accommodate this weight uncertainty, the DRSS method is capable of reliably identifying unnecessary samples and features under any future distribution within a specified range. We provide a theoretical guarantee of the DRSS method and validate its performance through numerical experiments on both synthetic and real-world datasets. |
| title | Distributionally Robust Safe Screening |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.16328 |