Learning with a Wasserstein Loss
Annual Conference on Neural Information Processing Systems, 2015.
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
PPT (Upload PPT)