English
Related papers

Related papers: Inequalities for the Bayes Risk

200 papers

We present a new concentration of measure inequality for sums of independent bounded random variables, which we name a split-kl inequality. The inequality is particularly well-suited for ternary random variables, which naturally show up in…

Machine Learning · Statistics 2023-01-18 Yi-Shan Wu , Yevgeny Seldin

Bayesian inference typically requires the computation of an approximation to the posterior distribution. An important requirement for an approximate Bayesian inference algorithm is to output high-accuracy posterior mean and uncertainty…

Statistics Theory · Mathematics 2018-10-03 Jonathan H. Huggins , Trevor Campbell , Mikołaj Kasprzak , Tamara Broderick

We give several inequalities on generalized entropies involving Tsallis entropies, using some inequalities obtained by improvements of Young's inequality. We also give a generalized Han's inequality.

Classical Analysis and ODEs · Mathematics 2013-01-08 S. Furuichi , N. Minculete , F. -C. Mitroi

Certain excess versions of the Minkowski and H\"older inequalities are given. These new results generalize and improve the Minkowski and H\"older inequalities.

Probability · Mathematics 2018-07-31 Iosif Pinelis

We obtain simple proofs of certain inequalites for bivariate means.

Classical Analysis and ODEs · Mathematics 2011-05-04 Jozsef Sandor

Sharp extensions of Pitt's inequality and bounds for Stein-Weiss fractional integrals are obtained that incorporate gradient forms and vector-valued operators. Such results include Hardy-Rellich inequalities.

Analysis of PDEs · Mathematics 2007-05-23 William Beckner

We present a class of inequality constraints on the set of distributions induced by local interventions on variables governed by a causal Bayesian network, in which some of the variables remain unmeasured. We derive bounds on causal effects…

Artificial Intelligence · Computer Science 2012-07-02 Changsung Kang , Jin Tian

We provide a compendium of inequalities between several quantum state distinguishability measures. For each measure these inequalities consist of the sharpest possible upper and lower bounds in terms of another measure. Some of these…

Quantum Physics · Physics 2014-10-24 Koenraad M. R. Audenaert

Two approaches to hypothesis testing, e-value testing and Bayes risk minimisation, both invoke Markov's inequality to control error probabilities. They differ in which distribution certifies the unit-moment condition: the null for Type I…

Statistics Theory · Mathematics 2026-04-02 Nicholas G. Polson , Daniel Zantedeschi

We consider the sum of squared logarithms inequality and investigate possible connections with the theory of majorization. We also discuss alternative sufficient conditions on two sets of vectors $a,b\in\mathbb{R}_+^n$ so that…

Classical Analysis and ODEs · Mathematics 2015-07-31 Fozi M. Dannan , Patrizio Neff , Christian Thiel

This work proposes a wavelet shrinkage rule under asymmetric LINEX loss function and a mixture of a point mass function at zero and the logistic distribution as prior distribution to the wavelet coefficients in a nonparametric regression…

Methodology · Statistics 2023-07-27 Alex Rodrigo dos Santos Sousa

We show that the unified method recently proposed by Feldman and Cousins to put confidence intervals on bounded parameters cannot avoid the possibility of getting null results. A modified bayesian approach is also proposed (although not…

High Energy Physics - Experiment · Physics 2007-05-23 J. Bouchez

Initially motivated by their relevance in foundations of quantum mechanics and more recently by their applications in different contexts of quantum information science, violations of Bell inequalities have been extensively studied during…

Quantum Physics · Physics 2018-10-17 Carlos Palazuelos

Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an important role in deriving probabilistic guarantees in learning theory, information theory, and…

Information Theory · Computer Science 2026-05-28 Yanxiao Liu , Yijun Fan , Deniz Gündüz

We consider the problem of estimating the probability of error in multi-hypothesis testing when MAP criterion is used. This probability, which is also known as the Bayes risk is an important measure in many communication and information…

Information Theory · Computer Science 2007-07-16 Nandakishore Santhi , Alexander Vardy

We discuss general Bell inequalities for bipartite and multipartite systems, emphasizing the connection with convex geometry on the mathematical side, and the communication aspects on the physical side. Known results on families of…

Quantum Physics · Physics 2007-05-23 Reinhard F. Werner , Michael M. Wolf

In this paper, we present a generalized Bell inequality for mixed states. The distinct characteristic is that the inequality has variable bound depending on the decomposition of the density matrix. The inequality has been shown to be more…

Quantum Physics · Physics 2007-05-23 Chang-shui Yu , He-shan Song

The Wasserstein distance between probability measures on compact spaces provides a natural invariant quantitative measure of equidistribution, which is partly similar to the classical discrepancy appearing in Erd\"os-Tur\'an type…

Number Theory · Mathematics 2025-07-29 Emmanuel Kowalski , Théo Untrau

We obtain the tail probability of generalized sub-Gaussian canonical processes. It can be viewed as a variant of the Bernstein-type inequality in the i.i.d case, and we further get a tighter bound of concentration inequality through…

Probability · Mathematics 2024-02-02 Yiming Chen , Yuxuan Wang , Kefan Zhu

ReRecent studies in machine learning are based on models in which parameters or state variables are bounded restricted. These restrictions are from prior information to ensure the validity of scientific theories or structural consistency…

Methodology · Statistics 2024-01-26 Solmaz Seifollahi , Hossein Bevrani , Kristofer Mansson