Timezone: »

 
Poster
Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance
Giulia Luise · Alessandro Rudi · Massimiliano Pontil · Carlo Ciliberto

Wed Dec 05 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #153
in Wed Poster Session A »

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.

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

Author Information

Giulia Luise (University College London)
Alessandro Rudi (INRIA, Ecole Normale Superieure)
Massimiliano Pontil (IIT)
Carlo Ciliberto (Imperial College London)

More from the Same Authors