English
Related papers

Related papers: Tight Bounds for Jensen's Gap with Applications to…

200 papers

Variational inference (VI) is widely used for approximate inference in Bayesian machine learning. In addition to this practical success, generalization bounds for variational inference and related algorithms have been developed, mostly…

Machine Learning · Computer Science 2025-02-19 Yadi Wei , Roni Khardon

In this note we prove Jensen-type inequality for certain non-convex functions. We apply our idea to prove some inequalities which were suggested at some high-level math olympiades.

History and Overview · Mathematics 2013-12-04 Adilsultan Lepes

Given a function $f$ defined on a nonempty and convex subset of the $d$-dimensional Euclidean space, we prove that if $f$ is bounded from below and it satisfies a convexity-type functional inequality with infinite convex combinations, then…

Classical Analysis and ODEs · Mathematics 2025-09-16 Matyas Barczy , Zsolt Páles

Shape estimation and object reconstruction are common problems in image analysis. Mathematically, viewing objects in the image plane as random sets reduces the problem of shape estimation to inference about sets. Currently existing…

Methodology · Statistics 2009-03-12 Larissa I. Stanberry , Hanna K. Jankowski

Jensen's operator inequality for convexifiable functions is obtained. This result contains classical Jensen's operator inequality as a particular case. As a consequence, a new refinement and a reverse of Young's inequality is given.

Functional Analysis · Mathematics 2018-01-11 Hamid Reza Moradi , Shigeru Furuichi , Flavia-Corina Mitroi-Symeonidis , Razieh Naseri

We prove a matrix inequality for convex functions of a Hermitian matrix on a bipartite space. As an application we reprove and extend some theorems about eigenvalue asymptotics of Schr\"odinger operators with homogeneous potentials. The…

Mathematical Physics · Physics 2025-02-14 Eric A. Carlen , Rupert L. Frank , Simon Larson

In queueing theory, Lorden's inequality can be used for bounds estimation of the moments of backward and forward renewal times. Two random variables called backwards renewal time and forward renewal time for this process are defined.…

Probability · Mathematics 2021-08-27 Elmira Yu. Kalimulina , Galina A. Zverkina

We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression, and variants of this problem including constraints on the parameters of the linear combination. When the input…

Machine Learning · Statistics 2010-07-06 Jean-Yves Audibert , Olivier Catoni

For any given partial order in a $d$-dimensional euclidean space, under mild regularity assumptions, we show that the intersection of closed (generalized) intervals containing more than 1/2 of the probability mass, is a non-empty compact…

Statistics Theory · Mathematics 2012-11-05 Djordje Baljozovic , Milan Merkle

The main purpose of this paper is to establish a noncommutative analogue of the Efron--Stein inequality, which bounds the variance of a general function of some independent random variables. Moreover, we state an operator version including…

Functional Analysis · Mathematics 2021-07-23 Ali Talebi , Mohammad Sal Moslehian

We prove new concentration estimates for random variables that are functionals of a Poisson measure defined on a general measure space. Our results are specifically adapted to geometric applications, and are based on a pervasive use of a…

Probability · Mathematics 2015-04-14 Sascha Bachmann , Giovanni Peccati

We study the discrepancy between the distribution of a vector-valued functional of i.i.d. random elements and that of a Gaussian vector. Our main contribution is an explicit bound on the convex distance between the two distributions,…

Probability · Mathematics 2022-03-25 Mikołaj J. Kasprzak , Giovanni Peccati

In transfer learning, training and testing data sets are drawn from different data distributions. The transfer generalization gap is the difference between the population loss on the target data distribution and the training loss. The…

Machine Learning · Computer Science 2021-01-26 Sharu Theresa Jose , Osvaldo Simeone

In this paper we derive tight bounds on the expected value of products of {\em low influence} functions defined on correlated probability spaces. The proofs are based on extending Fourier theory to an arbitrary number of correlated…

Probability · Mathematics 2009-06-01 Elchanan Mossel

Comparative convexity is a generalization of convexity relying on abstract notions of means. We define the Jensen divergence and the Jensen diversity from the viewpoint of comparative convexity, and show how to obtain the generalized…

Information Theory · Computer Science 2017-05-05 Frank Nielsen , Richard Nock

Tight bounds for several symmetric divergence measures are introduced, given in terms of the total variation distance. Each of these bounds is attained by a pair of 2 or 3-element probability distributions. An application of these bounds…

Information Theory · Computer Science 2016-11-15 Igal Sason

Variational inference, as an alternative to Markov chain Monte Carlo sampling, has played a transformative role in enabling scalable computation for complex Bayesian models. Nevertheless, existing approaches often depend on either rigid…

Methodology · Statistics 2026-05-21 Somjit Roy , Pritam Dey , Debdeep Pati , Bani K. Mallick

The measure of Jensen-Fisher divergence between probability distributions is introduced and its theoretical grounds set up. This quantity, in contrast to the remaining Jensen divergences, is very sensitive to the fluctuations of the…

Information Theory · Computer Science 2013-01-08 P. Sánchez-Moreno , A. Zarzo , J. S. Dehesa

Limit theorems for non-additive probabilities or non-linear expectations are challenging issues which have raised progressive interest recently. The purpose of this paper is to study the strong law of large numbers and the law of the…

Probability · Mathematics 2016-08-03 Li-Xin Zhang

We present new PAC-Bayesian generalisation bounds for learning problems with unbounded loss functions. This extends the relevance and applicability of the PAC-Bayes learning framework, where most of the existing literature focuses on…

Machine Learning · Statistics 2021-12-16 Maxime Haddouche , Benjamin Guedj , Omar Rivasplata , John Shawe-Taylor