Learning with a Wasserstein Loss

06/17/2015
by   Charlie Frogner, et al.
0

Learning to predict multi-label outputs is challenging, but in many problems there is a natural metric on the outputs that can be used to improve predictions. In this paper we develop a loss function for multi-label learning, based on the Wasserstein distance. The Wasserstein distance provides a natural notion of dissimilarity for probability measures. Although optimizing with respect to the exact Wasserstein distance is costly, recent work has described a regularized approximation that is efficiently computed. We describe an efficient learning algorithm based on this regularization, as well as a novel extension of the Wasserstein distance from probability measures to unnormalized measures. We also describe a statistical learning bound for the loss. The Wasserstein loss can encourage smoothness of the predictions with respect to a chosen metric on the output space. We demonstrate this property on a real-data tag prediction problem, using the Yahoo Flickr Creative Commons dataset, outperforming a baseline that doesn't use the metric.

READ FULL TEXT

page 8

page 15

page 17

research
03/02/2021

Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)

Wasserstein GANs are based on the idea of minimising the Wasserstein dis...
research
10/12/2020

Permutation invariant networks to learn Wasserstein metrics

Understanding the space of probability measures on a metric space equipp...
research
06/01/2023

Hinge-Wasserstein: Mitigating Overconfidence in Regression by Classification

Modern deep neural networks are prone to being overconfident despite the...
research
08/25/2022

A deep learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation

Wasserstein-Fisher-Rao (WFR) distance is a family of metrics to gauge th...
research
08/15/2019

Using Wasserstein-2 regularization to ensure fair decisions with Neural-Network classifiers

In this paper, we propose a new method to build fair Neural-Network clas...
research
04/24/2018

Data-driven regularization of Wasserstein barycenters with an application to multivariate density registration

We present a framework to simultaneously align and smooth data in the fo...
research
03/01/2021

Computationally Efficient Wasserstein Loss for Structured Labels

The problem of estimating the probability distribution of labels has bee...

Please sign up or login with your details

Forgot password? Click here to reset