The Multimarginal Optimal Transport Formulation of Adversarial Multiclass Classification

04/27/2022
by   Nicolas Garcia Trillos, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2020

Dual Regularized Optimal Transport

In this paper, we present a new formulation of unbalanced optimal transp...
research
05/01/2019

On Scalable and Efficient Computation of Large Scale Optimal Transport

Optimal Transport (OT) naturally arises in many machine learning applica...
research
06/11/2020

Achieving robustness in classification using optimal transport with hinge regularization

We propose a new framework for robust binary classification, with Deep N...
research
09/13/2021

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

In this paper we explore the relation between distributionally robust le...
research
11/26/2021

The Geometry of Adversarial Training in Binary Classification

We establish an equivalence between a family of adversarial training pro...
research
12/05/2019

Adversarial Risk via Optimal Transport and Optimal Couplings

The accuracy of modern machine learning algorithms deteriorates severely...
research
01/22/2022

The Many Faces of Adversarial Risk

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

Please sign up or login with your details

Forgot password? Click here to reset