Bayes posterior convergence for loss functions via almost additive thermodynamic formalism

DOI10.1007/s10955-022-02885-8zbMath1493.62131arXiv2012.05601OpenAlexW3112477384MaRDI QIDQ2116497

Paulo Varandas, Artur Oscar Lopes, Sílvia R. C. Lopes

Publication date: 17 March 2022

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

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

zbMATH Keywords

thermodynamic formalismlarge deviationsBayesian inferenceGibbs posterior convergence

Mathematics Subject Classification ID

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

Related Items (2)

Decision theory and large deviations for dynamical hypotheses tests: the Neyman-Pearson lemma, min-max and Bayesian tests ⋮ Dynamical hypothesis tests and decision theory for Gibbs distributions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Recursive pathways to marginal likelihood estimation with prior-sensitivity analysis
• Escort distributions minimizing the Kullback-Leibler divergence for a large deviations principle and tests of entropy level
• The maximizing set of the asymptotic normalized log-likelihood for partially observed Markov chains
• Growth properties of power-free languages
• Thermodynamic formalism and applications to dimension theory
• Additive, almost additive and asymptotically additive potential sequences are equivalent
• How Gibbs distributions may naturally arise from synaptic adaptation mechanisms. A model-based argumentation
• Nonadditive thermodynamic formalism: Equilibrium and Gibbs measures
• Entropy, pressure and duality for Gibbs plans in ergodic transport
• Gibbs posterior for variable selection in high-dimensional classification and data mining
• Lyapunov spectrum of asymptotically sub-additive potentials
• Estimating functionals of one-dimensional Gibbs states
• Analycity properties of the characteristic exponents of random matrix products
• Relative entropy and identification of Gibbs measures in dynamical systems
• Lyapunov exponents for products of matrices and multifractal analysis. I: Positive matrices
• Chaotic hypothesis: Onsager reciprocity and fluctuation-dissipation theorem.
• A formula with some applications to the theory of Lyapunov exponents
• Theory of statistics
• Duality theorems in ergodic transport
• The calculus of thermodynamical formalism
• Nonequilibrium in thermodynamic formalism: the second law, gases and information geometry
• Nonequilibrium and fluctuation relation
• Posterior consistency for partially observed Markov models
• Introductory statistics and random phenomena. Uncertainty, complexity and chaotic behavior in engineering and science. With Mathematica uncertain virtual worlds by Bernard Ycart
• Consistency of the maximum likelihood estimator for general hidden Markov models
• Multifractal analysis of asymptotically additive sequences
• Entropic dynamics, time and quantum theory
• Large Deviations in Dynamical Systems and Stochastic Processes
• Entropy and large deviation
• A subadditive thermodynamic formalism for mixing repellers
• Two-Scale Difference Equations II. Local Regularity, Infinite Products of Matrices and Fractals
• Relative entropy, dimensions and large deviations forg-measures
• Nonequilibrium thermodynamics and information theory: basic concepts and relaxing dynamics
• Weak Gibbs measures: speed of convergence to entropy, topological and geometrical aspects
• Lyapunov Exponents for Quantum Channels: An Entropy Formula and Generic Properties
• Bayesian Probability Theory
• A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures
• A General Framework for Updating Belief Distributions
• Noncommuting Random Products
• A Variational Characterization of Finite Markov Chains
• Large deviations for empirical entropies ofg-measures
• Probability and Statistics by Example
• Equilibrium states and the ergodic theory of Anosov diffeomorphisms

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