Stein's density approach and information inequalities

DOI10.1214/ECP.V18-2578zbMATH Open1307.60009arXiv1210.3921OpenAlexW2111698756MaRDI QIDQ742967FDOQ742967

Christophe Ley, Yvik Swan

Publication date: 22 September 2014

Published in: Electronic Communications in Probability (Search for Journal in Brave)

Abstract: We provide a new perspective on Stein's so-called density approach by introducing a new operator and characterizing class which are valid for a much wider family of probability distributions on the real line. We prove an elementary factorization property of this operator and propose a new Stein identity which we use to derive information inequalities in terms of what we call the emph{generalized Fisher information distance}. We provide explicit bounds on the constants appearing in these inequalities for several important cases. We conclude with a comparison between our results and known results in the Gaussian case, hereby improving on several known inequalities from the literature.

Full work available at URL: https://arxiv.org/abs/1210.3921

Recommendations

• Stein's method, logarithmic Sobolev and transport inequalities
• First-order covariance inequalities via Stein's method
• Stein's density method for multivariate continuous distributions
• Weighted Poincaré inequalities, concentration inequalities and tail bounds related to Stein kernels in dimension one
• On Stein's identity and its applications

zbMATH Keywords

probability metricsgeneralized Fisher informationPinsker's inequalitymagic factorsStein's density approach

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Central limit and other weak theorems (60F05) Measures of information, entropy (94A17)

Cited In (25)

• Estimation with infinite-dimensional exponential family and Fisher divergence
• Efficient Multimodal Sampling via Tempered Distribution Flow
• On algebraic Stein operators for Gaussian polynomials
• Characterizations of non-normalized discrete probability distributions and their application in statistics
• A general parametric Stein characterization
• Parametric Stein operators and variance bounds
• Stein's identities and the related topics: an instructive explanation on shrinkage, characterization, normal approximation and goodness-of-fit
• Minimum L^q‐distance estimators for non‐normalized parametric models
• Fisher information and the fourth moment theorem
• Approximating by convolution of the normal and compound Poisson laws via Stein's method
• New bounds for the solution and derivatives of the Stein equation for the generalized inverse Gaussian and Kummer distributions
• Characterizations of GIG laws: a survey
• Maximal correlation and monotonicity of free entropy and of Stein discrepancy
• Approximation Results for Sums of Independent Random Variables
• Fixed point characterizations of continuous univariate probability distributions and their applications
• The informational gain from Stein and hierarchial Stein estimators
• Entropy and the fourth moment phenomenon
• Logistic or not Logistic?
• Title not available (Why is that?)
• First-order covariance inequalities via Stein's method
• A new characterization of the Gamma distribution and associated goodness-of-fit tests
• About the Stein equation for the generalized inverse Gaussian and Kummer distributions
• Stein's density method for multivariate continuous distributions
• Stein variational gradient descent with learned direction
• Goodness-of-fit tests for the Weibull distribution based on the Laplace transform and Stein's method

This page was built for publication: Stein's density approach and information inequalities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q742967)