Sinkhorn Barycenters with Free Support via Frank-Wolfe Algorithm

Giulia Luise, Saverio Salzo, Massimiliano Pontil, Carlo Ciliberto

Neural Information Processing Systems 

We present a novel algorithm to estimate the barycenter of arbitrary probability distributions with respect to the Sinkhorn divergence. Based on a Frank-Wolfe optimization strategy, our approach proceeds by populating the support of the barycenter incrementally, without requiring any pre-allocation.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found