no code implementations • 25 Sep 2019 • Youssef Mroueh*, Igor Melnyk*, Pierre Dognin*, Jerret Ross*, Tom Sercu*
We propose a new variational lower bound on the KL divergence and show that the Mutual Information (MI) can be estimated by maximizing this bound using a witness function on a hypothesis function class and an auxiliary scalar variable.
no code implementations • ICLR 2019 • Pierre Dognin*, Igor Melnyk*, Youssef Mroueh*, Jarret Ross*, Cicero Dos Santos*, Tom Sercu*
In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters.