Rademacher Complexity for Distributionally Robust Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 29098-29106
DOI: 10.1609/aaai.v40i34.40147 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhengyu Zhou und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
The goal of distributionally robust learning is to learn models capable of performing well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. Recently, Duchi and Namkoong (2021) have proven an upper bound for the excess risk of distributionally robust learning through the lens of covering number argument. However, there are situations where the covering argument fails. This motivates us to study the generalization bound through the lens of Rademacher complexity. More specifically, we consider the Cressie-Read divergence, f sub k of t is proportional to t to the k minus one. Our theoretical results indicate that the excess risk is of the order big O sub P of n to the negative one over two k star, where k star equals k over k minus one. The decay rate of the excess risk increases with increasing k. As illustrative examples, we consider three learning settings: 1) linear classifier; 2) Gaussian reproducing kernel Hilbert space; 3) one-hidden-layer networks. The empirical results validate our theoretical findings.
Zitieren
APA
Zhou, Z., & Liu, W. (2026). Rademacher Complexity for Distributionally Robust Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 29098-29106. https://doi.org/10.1609/aaai.v40i34.40147
Vancouver
Zhou Z, Liu W. Rademacher Complexity for Distributionally Robust Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):29098-29106. doi:10.1609/aaai.v40i34.40147
BibTeX
@article{Zhou2026,
author = {Zhou, Zhengyu and Liu, Weiwei},
title = {Rademacher Complexity for Distributionally Robust Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {34},
pages = {29098--29106},
doi = {10.1609/aaai.v40i34.40147}
}
EUVIMED