Abstract
Distributionally robust optimization (DRO) studies parameter estimation under uncertainty in the underlying probability distribution and has emerged as a principled framework for analyzing robustness and generalization. In particular, Wasserstein DRO, with distributional uncertainty induced by the Wasserstein distance, generalizes several popular regularizers. This paper studies Wasserstein DRO linear regression, unifying square-root Lasso and adversarial linear regression as important special cases. We prove that many properties of these two special cases carry over to this general method. In particular, we show (i) deterministic and non-asymptotic in-sample error bounds $O(n^{-1/2})$ in general and $O(n^{-1})$ under design matrix and sparsity conditions; (ii) insensitivity to the noise level, also known as the pivotal property; and (iii) solution equivalences for small and large ambiguity sets. The key proof step is to recast the method into a quadratic form, mimicking adversarial linear regression. We also show that the method can be solved efficiently, and we validate our findings through numerical simulations.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Stefansson, E., Vävinggren, D., & Ribeiro, A. H. (2026). Distributionally robust linear regression through the lens of adversarial training. https://omanscience.com/en/articles/distributionally-robust-linear-regression-through-the-lens-of-adversarial-training
MLA 9
Stefansson, Elis, et al. "Distributionally robust linear regression through the lens of adversarial training." https://omanscience.com/en/articles/distributionally-robust-linear-regression-through-the-lens-of-adversarial-training.
Chicago (author–date)
Stefansson, Elis, David Vävinggren, and Antônio H. Ribeiro. 2026. "Distributionally robust linear regression through the lens of adversarial training." https://omanscience.com/en/articles/distributionally-robust-linear-regression-through-the-lens-of-adversarial-training.
Harvard
Stefansson, E., Vävinggren, D. and Ribeiro, A. H. (2026) 'Distributionally robust linear regression through the lens of adversarial training', Available at: https://omanscience.com/en/articles/distributionally-robust-linear-regression-through-the-lens-of-adversarial-training.
Vancouver
Stefansson E, Vävinggren D, Ribeiro AH. Distributionally robust linear regression through the lens of adversarial training. https://omanscience.com/en/articles/distributionally-robust-linear-regression-through-the-lens-of-adversarial-training
IEEE
E. Stefansson, D. Vävinggren, and A. H. Ribeiro, "Distributionally robust linear regression through the lens of adversarial training," https://omanscience.com/en/articles/distributionally-robust-linear-regression-through-the-lens-of-adversarial-training.