English
Related papers

Related papers: Sharp Inequalities between Total Variation and Hel…

200 papers

We give a proof that, under relatively mild conditions, fully-connected feed-forward deep random neural networks converge to a Gaussian mixture distribution as only the width of the last hidden layer goes to infinity. We conducted…

Machine Learning · Statistics 2022-04-27 Yasuhiko Asao , Ryotaro Sakamoto , Shiro Takagi

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…

Probability · Mathematics 2023-08-03 Clément L. Canonne

We prove minimax bounds for estimating Gaussian location mixtures on $\mathbb{R}^d$ under the squared $L^2$ and the squared Hellinger loss functions. Under the squared $L^2$ loss, we prove that the minimax rate is upper and lower bounded by…

Statistics Theory · Mathematics 2021-05-20 Arlene K. H. Kim , Adityanand Guntuboyina

Given two high-dimensional Gaussians with the same mean, we prove a lower and an upper bound for their total variation distance, which are within a constant factor of one another.

Statistics Theory · Mathematics 2023-10-24 Luc Devroye , Abbas Mehrabian , Tommy Reddad

Pinsker's classical inequality asserts that the total variation $TV(\mu, \nu)$ between two probability measures is bounded by $\sqrt{ 2H(\mu|\nu)}$ where $H$ denotes the relative entropy (or Kullback-Leibler divergence). Considering the…

Probability · Mathematics 2025-06-30 Mathias Beiglböck , Markus Zona

In this article, we consider products of ergodic Markov chains and discuss their cutoffs in the total variation. Through a new inequality relating the total variation and the Hellinger distance, we may identify the total variation cutoffs…

Probability · Mathematics 2017-02-13 Guan-Yu Chen , Takashi Kumagai

Uncertainty propagation in non-linear dynamical systems has become a key problem in various fields including control theory and machine learning. In this work we focus on discrete-time non-linear stochastic dynamical systems. We present a…

Systems and Control · Electrical Eng. & Systems 2024-09-12 Eduardo Figueiredo , Andrea Patane , Morteza Lahijanian , Luca Laurenti

Total variation distance (TV distance) is an important measure for the difference between two distributions. Recently, there has been progress in approximating the TV distance between product distributions: a deterministic algorithm for a…

Data Structures and Algorithms · Computer Science 2023-09-27 Weiming Feng , Liqiang Liu , Tianren Liu

Many scientific and engineering problems require to perform Bayesian inferences in function spaces, in which the unknowns are of infinite dimension. In such problems, choosing an appropriate prior distribution is an important task. In…

Methodology · Statistics 2016-06-22 Zhewei Yao , Zixi Hu , Jinglai Li

In this paper, we consider using total variation minimization to recover signals whose gradients have a sparse support, from a small number of measurements. We establish the proof for the performance guarantee of total variation (TV)…

Information Theory · Computer Science 2013-10-14 Jian-Feng Cai , Weiyu Xu

In this paper, we establish a novel connection between total variation (TV) distance estimation and probabilistic inference. In particular, we present an efficient, structure-preserving reduction from relative approximation of TV distance…

Data Structures and Algorithms · Computer Science 2024-07-02 Arnab Bhattacharyya , Sutanu Gayen , Kuldeep S. Meel , Dimitrios Myrisiotis , A. Pavan , N. V. Vinodchandran

This work considers the use of Total variation (TV) minimization in the recovery of a given gradient sparse vector from Gaussian linear measurements. It has been shown in recent studies that there exist a sharp phase transition behavior in…

Information Theory · Computer Science 2019-02-11 Sajad Daei , Farzan Haddadi , Arash Amini

We develop sharp bounds on the statistical distance between high-dimensional permutation mixtures and their i.i.d. counterparts. Our approach establishes a new geometric link between the spectrum of a complex channel overlap matrix and the…

Statistics Theory · Mathematics 2025-09-17 Yiguo Liang , Yanjun Han

This work introduces a new, explicit bound on the Hellinger distance between a continuous random variable and a Gaussian with matching mean and variance. As example applications, we derive a quantitative Hellinger central limit theorem and…

Probability · Mathematics 2025-09-23 Morgane Austern , Lester Mackey

We quantify the parameter stability of a spherical Gaussian Mixture Model (sGMM) under small perturbations in distribution space. Namely, we derive the first explicit bound to show that for a mixture of spherical Gaussian $P$ (sGMM) in a…

Machine Learning · Statistics 2023-02-02 Hanyu Zhang , Marina Meila

Mixture distributions arise in many parametric and non-parametric settings -- for example, in Gaussian mixture models and in non-parametric estimation. It is often necessary to compute the entropy of a mixture, but, in most cases, this…

Information Theory · Computer Science 2022-11-22 Artemy Kolchinsky , Brendan D. Tracey

The Kullback-Leibler divergence, the Kullback-Leibler variation, and the Bernstein "norm" are used to quantify discrepancies among probability distributions in likelihood models such as nonparametric maximum likelihood and nonparametric…

Statistics Theory · Mathematics 2026-01-27 Tetsuya Kaji

$f$-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics and information theory such as Kullback-Leibler…

Statistics Theory · Mathematics 2013-10-16 Adityanand Guntuboyina , Sujayam Saha , Geoffrey Schiebinger

We focus on Bayesian inverse problems with Gaussian likelihood, linear forward model, and priors that can be formulated as a Gaussian mixture. Such a mixture is expressed as an integral of Gaussian density functions weighted by a mixing…

Computation · Statistics 2024-08-30 Rafael Flock , Yiqiu Dong , Felipe Uribe , Olivier Zahm

We show that the square Hellinger distance between two Bayesian networks on the same directed graph, $G$, is subadditive with respect to the neighborhoods of $G$. Namely, if $P$ and $Q$ are the probability distributions defined by two…

Machine Learning · Computer Science 2016-12-12 Constantinos Daskalakis , Qinxuan Pan