Distributionally Robust Safe Screening
This work addresses the challenge of model robustness and efficiency in machine learning under distribution shifts, but it appears incremental as it extends existing techniques rather than introducing a fundamentally new approach.
The authors tackled the problem of identifying unnecessary samples and features in distributionally robust covariate shift settings by proposing the DRSS method, which combines distributionally robust learning with safe screening, and validated it with theoretical guarantees and experiments on synthetic and real-world datasets.
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.