DeepAI AI Chat
Log In Sign Up

The Multimarginal Optimal Transport Formulation of Adversarial Multiclass Classification

by   Nicolas Garcia Trillos, et al.

We study a family of adversarial multiclass classification problems and provide equivalent reformulations in terms of: 1) a family of generalized barycenter problems introduced in the paper and 2) a family of multimarginal optimal transport problems where the number of marginals is equal to the number of classes in the original classification problem. These new theoretical results reveal a rich geometric structure of adversarial learning problems in multiclass classification and extend recent results restricted to the binary classification setting. A direct computational implication of our results is that by solving either the barycenter problem and its dual, or the MOT problem and its dual, we can recover the optimal robust classification rule and the optimal adversarial strategy for the original adversarial problem. Examples with synthetic and real data illustrate our results.


page 1

page 2

page 3

page 4


Dual Regularized Optimal Transport

In this paper, we present a new formulation of unbalanced optimal transp...

On Scalable and Efficient Computation of Large Scale Optimal Transport

Optimal Transport (OT) naturally arises in many machine learning applica...

Achieving robustness in classification using optimal transport with hinge regularization

We propose a new framework for robust binary classification, with Deep N...

On the regularized risk of distributionally robust learning over deep neural networks

In this paper we explore the relation between distributionally robust le...

Adversarial Risk via Optimal Transport and Optimal Couplings

The accuracy of modern machine learning algorithms deteriorates severely...

The Geometry of Adversarial Training in Binary Classification

We establish an equivalence between a family of adversarial training pro...

The Many Faces of Adversarial Risk

Adversarial risk quantifies the performance of classifiers on adversaria...