English
Related papers

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

200 papers

In this paper we use basic properties of strongly convex functions to obtain new inequalities including Jensen's type and Jensen-Mercer type inequalities. Applications for special means are pointed out as well. We also give a Jensen's…

Functional Analysis · Mathematics 2017-07-06 H. R. Moradi , M. E. Omidvar , M. Adil Khan , K. Nikodem

In this paper, we give the refinement of an extension of Jensen's inequality to affine combinations. Furthermore, we present the functional form of Jensen's inequality for continuous 3-convex functions of one variable at a point.

Classical Analysis and ODEs · Mathematics 2016-01-25 Imran Abbas Baloch , Silvestru Sever Dragomir

The paper reexamines an argument by Talagrand that leads to a remarkable exponential tail bound for the concentration of probability near a set. The main novelty is the replacement of a mysterious Calculus inequality by an application of…

Probability · Mathematics 2007-05-23 David Pollard

A real valued function defined on}$\mathbb{R}$ {\small is called}$g${\small --convex if it satisfies the following \textquotedblleft generalized Jensen's inequality\textquotedblright under a given}$g${\small -expectation, i.e.,…

Probability · Mathematics 2008-02-05 Guangyan Jia , Shige Peng

The standard margin-based structured prediction commonly uses a maximum loss over all possible structured outputs. The large-margin formulation including latent variables not only results in a non-convex formulation but also increases the…

Machine Learning · Computer Science 2019-06-25 Kevin Bello , Jean Honorio

This note demonstrates that it is possible to bound the expectation of an arbitrary norm of a random matrix drawn from the Stiefel manifold in terms of the expected norm of a standard Gaussian matrix with the same dimensions. A related…

Probability · Mathematics 2014-04-29 Joel A. Tropp

In this note, we study the relationship between the variational gap and the variance of the (log) likelihood ratio. We show that the gap can be upper bounded by some form of dispersion measure of the likelihood ratio, which suggests the…

Machine Learning · Computer Science 2019-06-11 Chin-Wei Huang , Aaron Courville

In this paper we shall consider some famous means such as arithmetic, harmonic, geometric, root square mean, etc. Considering the difference of these means, we can establish. some inequalities among them. Interestingly, the difference of…

Information Theory · Computer Science 2011-03-29 Inder Jeet Taneja

Mercer inequality for convex functions is a variant of Jensen's inequality, with an operator version that is still valid without operator convexity. This paper is two folded. First, we present a Mercer-type inequality for operators without…

Functional Analysis · Mathematics 2020-03-06 H. R. Moradi , S. Furuichi , M. Sababheh

We generalize the Jensen-Shannon divergence by considering a variational definition with respect to a generic mean extending thereby the notion of Sibson's information radius. The variational definition applies to any arbitrary distance and…

Information Theory · Computer Science 2021-04-16 Frank Nielsen

This paper is devoted to present new error bounds of regularized gap functions for polynomial variational inequalities with exponents explicitly determined by the dimension of the underlying space and the number/degree of the involved…

Optimization and Control · Mathematics 2020-03-24 Dinh Bui Van , Tien-Son Pham

In this paper we develop tools for studying limit theorems by means of convexity. We establish bounds for the discrepancy in total variation between probability measures $\mu$ and $\nu$ such that $\nu$ is log-concave with respect to $\mu$.…

Probability · Mathematics 2022-10-24 Arturo Jaramillo , James Melbourne

We study a family of inequalities on pairs of measure spaces involving functions defined on product domains. Our main result establishes a Jensen-type inequality under a general product-measure framework, extending classical inequalities…

Functional Analysis · Mathematics 2026-03-09 P. D. Johnson , R. N. Mohapatra , Shankhadeep Mondal

Generalization in deep learning has been the topic of much recent theoretical and empirical research. Here we introduce desiderata for techniques that predict generalization errors for deep learning models in supervised learning. Such…

Machine Learning · Statistics 2020-12-10 Guillermo Valle-Pérez , Ard A. Louis

Variational inference has become an increasingly attractive fast alternative to Markov chain Monte Carlo methods for approximate Bayesian inference. However, a major obstacle to the widespread use of variational methods is the lack of…

Machine Learning · Statistics 2020-03-03 Jonathan H. Huggins , Mikołaj Kasprzak , Trevor Campbell , Tamara Broderick

We present a new PAC-Bayesian generalization bound. Standard bounds contain a $\sqrt{L_n \cdot \KL/n}$ complexity term which dominates unless $L_n$, the empirical error of the learning algorithm's randomized predictions, vanishes. We manage…

Machine Learning · Computer Science 2021-12-16 Zakaria Mhammedi , Peter D. Grunwald , Benjamin Guedj

Convexity is a key concept in information theory, namely via the many implications of Jensen's inequality, such as the non-negativity of the Kullback-Leibler divergence (KLD). Jensen's inequality also underlies the concept of Jensen-Shannon…

Information Theory · Computer Science 2008-04-11 Andre Martins , Pedro Aguiar , Mario Figueiredo

Divergences often play important roles for study in information science so that it is indispensable to investigate their fundamental properties. There is also a mathematical significance of such results. In this paper, we introduce some…

Statistical Mechanics · Physics 2011-10-19 S. Furuichi , F. -C. Mitroi

We develop a new framework for the Jensen-type inequalities that allows us to deal with functions not necessarily convex and Borel measures not necessarily positive.

Classical Analysis and ODEs · Mathematics 2012-07-31 Constantin P. Niculescu , Cătălin Irinel Spiridon

Generalization bounds which assess the difference between the true risk and the empirical risk, have been studied extensively. However, to obtain bounds, current techniques use strict assumptions such as a uniformly bounded or a Lipschitz…

Machine Learning · Computer Science 2022-11-03 Itai Gat , Yossi Adi , Alexander Schwing , Tamir Hazan