Skip to yearly menu bar Skip to main content


Poster

Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance

Giulia Luise · Alessandro Rudi · Massimiliano Pontil · Carlo Ciliberto

Room 517 AB #153

Keywords: [ Kernel Methods ] [ Learning Theory ] [ Structured Prediction ]


Abstract:

Applications of optimal transport have recently gained remarkable attention as a result of the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation to the Wasserstein distance is replaced by a regularized version that is less accurate but easy to differentiate. In this work we characterize the differential properties of the original Sinkhorn approximation, proving that it enjoys the same smoothness as its regularized version and we explicitly provide an efficient algorithm to compute its gradient. We show that this result benefits both theory and applications: on one hand, high order smoothness confers statistical guarantees to learning with Wasserstein approximations. On the other hand, the gradient formula allows to efficiently solve learning and optimization problems in practice. Promising preliminary experiments complement our analysis.

Live content is unavailable. Log in and register to view live content