Bayes posterior convergence for loss functions via almost additive thermodynamic formalism

DOI10.1007/S10955-022-02885-8zbMATH Open1493.62131arXiv2012.05601OpenAlexW3112477384MaRDI QIDQ2116497FDOQ2116497

A. O. Lopes, Paulo Varandas, Sílvia R. C. Lopes

Publication date: 17 March 2022

Published in: Journal of Statistical Physics (Search for Journal in Brave)

Abstract: Statistical inference can be seen as information processing involving input information and output information that updates belief about some unknown parameters. We consider the Bayesian framework for making inferences about dynamical systems from ergodic observations, where the Bayesian procedure is based on the Gibbs posterior inference, a decision process generalization of standard Bayesian inference where the likelihood is replaced by the exponential of a loss function. In the case of direct observation and almost-additive loss functions, we prove an exponential convergence of the a posteriori measures a limit measure. Our estimates on the Bayes posterior convergence for direct observation are related and extend those in a recent paper by K. McGoff, S. Mukherjee and A. Nobel. Our approach makes use of non-additive thermodynamic formalism and large deviation properties instead of joinings.

Full work available at URL: https://arxiv.org/abs/2012.05601

zbMATH Keywords

Bayesian inferencelarge deviationsthermodynamic formalismGibbs posterior convergence

Mathematics Subject Classification ID

Bayesian inference (62F15) Large deviations (60F10) Empirical decision procedures; empirical Bayes procedures (62C12) Characterization and structure theory of statistical distributions (62E10) Thermodynamic formalism, variational principles, equilibrium states for dynamical systems (37D35)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A General Framework for Updating Belief Distributions
• Recursive pathways to marginal likelihood estimation with prior-sensitivity analysis
• Entropy and large deviation
• Two-Scale Difference Equations II. Local Regularity, Infinite Products of Matrices and Fractals
• Equilibrium states and the ergodic theory of Anosov diffeomorphisms
• Relative entropy and identification of Gibbs measures in dynamical systems
• Chaotic hypothesis: Onsager reciprocity and fluctuation-dissipation theorem.
• Escort distributions minimizing the Kullback-Leibler divergence for a large deviations principle and tests of entropy level
• Large Deviations in Dynamical Systems and Stochastic Processes
• Large deviations for empirical entropies ofg-measures
• Gibbs posterior for variable selection in high-dimensional classification and data mining
• Theory of statistics
• Duality theorems in ergodic transport
• A subadditive thermodynamic formalism for mixing repellers
• Noncommuting Random Products
• Bayesian Probability Theory
• Consistency of the maximum likelihood estimator for general hidden Markov models
• Entropic dynamics, time and quantum theory
• Lyapunov exponents for products of matrices and multifractal analysis. I: Positive matrices
• Nonadditive thermodynamic formalism: Equilibrium and Gibbs measures
• Lyapunov spectrum of asymptotically sub-additive potentials
• The maximizing set of the asymptotic normalized log-likelihood for partially observed Markov chains
• A Variational Characterization of Finite Markov Chains
• How Gibbs distributions may naturally arise from synaptic adaptation mechanisms. A model-based argumentation
• Thermodynamic formalism and applications to dimension theory
• Analycity properties of the characteristic exponents of random matrix products
• Growth properties of power-free languages
• A formula with some applications to the theory of Lyapunov exponents
• Nonequilibrium and fluctuation relation
• A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures
• Entropy, pressure and duality for Gibbs plans in ergodic transport
• Multifractal analysis of asymptotically additive sequences
• Weak Gibbs measures: speed of convergence to entropy, topological and geometrical aspects
• Additive, almost additive and asymptotically additive potential sequences are equivalent
• Estimating functionals of one-dimensional Gibbs states
• Nonequilibrium in thermodynamic formalism: the second law, gases and information geometry
• The calculus of thermodynamical formalism
• Nonequilibrium thermodynamics and information theory: basic concepts and relaxing dynamics
• Posterior consistency for partially observed Markov models
• Relative entropy, dimensions and large deviations forg-measures
• Introductory statistics and random phenomena. Uncertainty, complexity and chaotic behavior in engineering and science. With Mathematica uncertain virtual worlds by Bernard Ycart
• Lyapunov Exponents for Quantum Channels: An Entropy Formula and Generic Properties
• Probability and statistics by example. Volume I: Basic probability and statistics.

Cited In (4)

• Dynamical hypothesis tests and decision theory for Gibbs distributions
• A Livšic-type theorem and some regularity properties for nonadditive sequences of potentials
• Decision theory and large deviations for dynamical hypotheses tests: the Neyman-Pearson lemma, min-max and Bayesian tests
• Gibbs posterior convergence and the thermodynamic formalism

This page was built for publication: Bayes posterior convergence for loss functions via almost additive thermodynamic formalism

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2116497)