Learning with a Wasserstein Loss

Annual Conference on Neural Information Processing Systems, 2015.

Cited by: 278|Views36
EI

Abstract:

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 probabi...More

Code:

Data:

Your rating :
0

 

Tags
Comments