We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter representation to derive a general f-divergence estimator based on two i.i.d. samples and derive the dual program for this estimator that performs well empirically. We also point out a connection between our estimator and MMD
17 pagesWe propose new change of measure inequalities based on $f$-divergences (of which the Kullbac...
The Jensen's inequality plays a crucial role to obtain inequalities for divergences between probabil...
In this work, the probability of an event under some joint distribution is bounded by measuring it w...
We show that the variational representations for f-divergences currently used in the litera-ture can...
This paper is focused on f-divergences, consisting of three main contributions. The first one introd...
f-divergences are a general class of divergences between probability measures which include as speci...
This paper introduces the $\textit{variational Rényi bound}$ (VR) that extends traditional variation...
We derive a generalized notion of f-divergences, called (f,l)-divergences. We show that this general...
We derive a generalized notion of f-divergences, called (f,l)-divergences. We show that this general...
We propose an approach for estimating f-divergences that exploits a new representa-tion of an f-dive...
Given two probability measures P and Q and an event E, we provide bounds on P(E) in terms of Q(E) an...
The f-divergence evaluates the dissimilarity between two probability distributions defined in terms ...
We unify f-divergences, Bregman divergences, surrogate regret bounds, proper scoring rules, cost cur...
Csiszár's f-divergence is a way to measure the similarity of two probability distributions. We study...
This paper introduces the $f$-EI$(\phi)$ algorithm, a novel iterative algorithm which operates on me...
17 pagesWe propose new change of measure inequalities based on $f$-divergences (of which the Kullbac...
The Jensen's inequality plays a crucial role to obtain inequalities for divergences between probabil...
In this work, the probability of an event under some joint distribution is bounded by measuring it w...
We show that the variational representations for f-divergences currently used in the litera-ture can...
This paper is focused on f-divergences, consisting of three main contributions. The first one introd...
f-divergences are a general class of divergences between probability measures which include as speci...
This paper introduces the $\textit{variational Rényi bound}$ (VR) that extends traditional variation...
We derive a generalized notion of f-divergences, called (f,l)-divergences. We show that this general...
We derive a generalized notion of f-divergences, called (f,l)-divergences. We show that this general...
We propose an approach for estimating f-divergences that exploits a new representa-tion of an f-dive...
Given two probability measures P and Q and an event E, we provide bounds on P(E) in terms of Q(E) an...
The f-divergence evaluates the dissimilarity between two probability distributions defined in terms ...
We unify f-divergences, Bregman divergences, surrogate regret bounds, proper scoring rules, cost cur...
Csiszár's f-divergence is a way to measure the similarity of two probability distributions. We study...
This paper introduces the $f$-EI$(\phi)$ algorithm, a novel iterative algorithm which operates on me...
17 pagesWe propose new change of measure inequalities based on $f$-divergences (of which the Kullbac...
The Jensen's inequality plays a crucial role to obtain inequalities for divergences between probabil...
In this work, the probability of an event under some joint distribution is bounded by measuring it w...