Distributionally Robust Safe Screening
Abstract
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.
Cite
@article{arxiv.2404.16328,
title = {Distributionally Robust Safe Screening},
author = {Hiroyuki Hanada and Satoshi Akahane and Tatsuya Aoyama and Tomonari Tanaka and Yoshito Okura and Yu Inatsu and Noriaki Hashimoto and Taro Murayama and Lee Hanju and Shinya Kojima and Ichiro Takeuchi},
journal= {arXiv preprint arXiv:2404.16328},
year = {2024}
}