AI Chat AI Image Generator AI Video Text to Speech

A short note on an inequality between KL and TV

02/15/2022

∙

by Clément L. Canonne, et al.

∙

∙

The goal of this short note is to discuss the relation between Kullback–Leibler divergence and total variation distance, starting with the celebrated Pinsker's inequality relating the two, before switching to a simple, yet (arguably) more useful inequality, apparently not as well known, due to Bretagnolle and Huber. We also discuss applications of this bound for minimax testing lower bounds.

research

∙ 03/01/2022

Tight bounds for augmented KL divergence in terms of augmented total variation distance

We provide optimal variational upper and lower bounds for the augmented ...

0 Michele Caprio, et al. ∙

research

∙ 07/14/2018

About the lower bounds for the multiple testing problem

Given an observed random variable, consider the problem of recovering it...

0 Yannick Baraud, et al. ∙

research

∙ 01/09/2018

Better and Simpler Error Analysis of the Sinkhorn-Knopp Algorithm for Matrix Scaling

Given a non-negative n × m real matrix A, the matrix scaling problem is...

0 Deeparnab Chakrabarty, et al. ∙

research

∙ 01/26/2023

A Bound for Stieltjes Constants

The goal of this note is to improve on the currently available bounds fo...

0 Sebastian Pauli, et al. ∙

research

∙ 12/15/2020

Squirrel: A Switching Hyperparameter Optimizer

In this short note, we describe our submission to the NeurIPS 2020 BBO c...

26 Noor Awad, et al. ∙

research

∙ 07/05/2018

Frame-constrained Total Variation Regularization for White Noise Regression

Despite the popularity and practical success of total variation (TV) reg...

0 Miguel del Álamo Ruiz, et al. ∙

research

∙ 08/28/2018

Exponential inequality for chaos based on sampling without replacement

We are interested in the behavior of particular functionals, in a framew...

0 P Hodara, et al. ∙