Search

Adversarial training is a min-max optimization problem that is designed to construct robust classifiers against adversarial perturbations of data. We study three models of adversarial training in the multiclass agnostic-classifier setting. We prove the existence of Borel measurable robust classifiers in each model and provide a unified perspective of the adversarial training problem, expanding the connections with optimal transport initiated by the authors in their previous work [21]. In addition, we develop new connections between adversarial training in the multiclass setting and total variation regularization. As a corollary of our results, we provide an alternative proof of the existence of Borel measurable solutions to the agnostic adversarial training problem in the binary classification setting.

Search Results

Refine search

Refine search

Actions for selected content:

1 results

On the existence of solutions to adversarial training in multiclass classification

Search Results

Refine search

Refine search

Actions for selected content:

Save Search

1 results

On the existence of solutions to adversarial training in multiclass classification