# Optimal Bounds between $f$-Divergences and Integral Probability Metrics

10 Jun 2020Rohit AgrawalThibaut Horel

The families of $f$-divergences (e.g. the Kullback-Leibler divergence) and Integral Probability Metrics (e.g. total variation distance or maximum mean discrepancies) are widely used to quantify the similarity between probability distributions. In this work, we systematically study the relationship between these two families from the perspective of convex duality... (read more)

PDF Abstract

No code implementations yet. Submit your code now