Bayes posterior convergence for loss functions via almost additive thermodynamic formalism
From MaRDI portal
Publication:2116497
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.
Recommendations
Cites work
- scientific article; zbMATH DE number 49597 (Why is no real title available?)
- scientific article; zbMATH DE number 3551675 (Why is no real title available?)
- scientific article; zbMATH DE number 592670 (Why is no real title available?)
- scientific article; zbMATH DE number 957411 (Why is no real title available?)
- A General Framework for Updating Belief Distributions
- A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures
- A Variational Characterization of Finite Markov Chains
- A formula with some applications to the theory of Lyapunov exponents
- A subadditive thermodynamic formalism for mixing repellers
- Additive, almost additive and asymptotically additive potential sequences are equivalent
- Analycity properties of the characteristic exponents of random matrix products
- Bayesian probability theory. Applications in the physical sciences
- Chaotic hypothesis: Onsager reciprocity and fluctuation-dissipation theorem.
- Consistency of the maximum likelihood estimator for general hidden Markov models
- Duality theorems in ergodic transport
- Entropic dynamics, time and quantum theory
- Entropy and large deviation
- Entropy, pressure and duality for Gibbs plans in ergodic transport
- Equilibrium states and the ergodic theory of Anosov diffeomorphisms
- Escort distributions minimizing the Kullback-Leibler divergence for a large deviations principle and tests of entropy level
- Estimating functionals of one-dimensional Gibbs states
- Gibbs posterior for variable selection in high-dimensional classification and data mining
- Growth properties of power-free languages
- How Gibbs distributions may naturally arise from synaptic adaptation mechanisms. A model-based argumentation
- Introductory statistics and random phenomena. Uncertainty, complexity and chaotic behavior in engineering and science. With Mathematica uncertain virtual worlds by Bernard Ycart
- Large Deviations in Dynamical Systems and Stochastic Processes
- Large deviations for empirical entropies ofg-measures
- Lyapunov Exponents for Quantum Channels: An Entropy Formula and Generic Properties
- Lyapunov exponents for products of matrices and multifractal analysis. I: Positive matrices
- Lyapunov spectrum of asymptotically sub-additive potentials
- Multifractal analysis of asymptotically additive sequences
- Nonadditive thermodynamic formalism: Equilibrium and Gibbs measures
- Noncommuting Random Products
- Nonequilibrium and fluctuation relation
- Nonequilibrium in thermodynamic formalism: the second law, gases and information geometry
- Nonequilibrium thermodynamics and information theory: basic concepts and relaxing dynamics
- Posterior consistency for partially observed Markov models
- Probability and statistics by example. Volume I: Basic probability and statistics.
- Recursive pathways to marginal likelihood estimation with prior-sensitivity analysis
- Relative entropy and identification of Gibbs measures in dynamical systems
- Relative entropy, dimensions and large deviations forg-measures
- Statistical theory. A concise introduction
- The calculus of thermodynamical formalism
- The maximizing set of the asymptotic normalized log-likelihood for partially observed Markov chains
- Theory of statistics
- Thermodynamic formalism and applications to dimension theory
- Two-Scale Difference Equations II. Local Regularity, Infinite Products of Matrices and Fractals
- Weak Gibbs measures: speed of convergence to entropy, topological and geometrical aspects
Cited in
(5)- 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
- Gibbs posterior convergence and the thermodynamic formalism
- The generalized IFS Bayesian method and an associated variational principle covering the classical and dynamical cases
- A Livšic-type theorem and some regularity properties for nonadditive sequences of potentials
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)
