Gibbs posterior convergence and the thermodynamic formalism

DOI10.1214/21-AAP1685zbMATH Open1493.62510OpenAlexW2913067311MaRDI QIDQ2117451FDOQ2117451

Authors Kevin McGoff, Sayan Mukherjee, Andrew B. Nobel 

Publication date 21 March 2022

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1901.08641

zbMATH Keywords

thermodynamic formalismGibbs measureBayesian posterior consistencyGibbs posterior principle

Mathematics Subject Classification ID

Non-Markovian processes: estimation (62M09) Thermodynamic formalism, variational principles, equilibrium states for dynamical systems (37D35)

Abstract: In this paper we consider a Bayesian framework for making inferences about dynamical systems from ergodic observations. The proposed Bayesian procedure is based on the Gibbs posterior, a decision theoretic generalization of standard Bayesian inference. We place a prior over a model class consisting of a parametrized family of Gibbs measures on a mixing shift of finite type. This model class generalizes (hidden) Markov chain models by allowing for long range dependencies, including Markov chains of arbitrarily large orders. We characterize the asymptotic behavior of the Gibbs posterior distribution on the parameter space as the number of observations tends to infinity. In particular, we define a limiting variational problem over the space of joinings of the model system with the observed system, and we show that the Gibbs posterior distributions concentrate around the solution set of this variational problem. In the case of properly specified models our convergence results may be used to establish posterior consistency. This work establishes tight connections between Gibbs posterior inference and the thermodynamic formalism, which may inspire new proof techniques in the study of Bayesian posterior consistency for dependent processes.

Recommendations

• Bayes posterior convergence for loss functions via almost additive thermodynamic formalism
• scientific article; zbMATH DE number 224091
• Estimating Bayes factors via thermodynamic integration and population MCMC
• Bayesian approach to thermostatistics
• Thermodynamic Bayesian model comparison
• Thermodynamic integration and steppingstone sampling methods for estimating Bayes factors: a tutorial
• On the properties of variational approximations of Gibbs posteriors
• Gibbs sampling, conjugate priors and coupling
• Convergence of Gibbs Measures Associated with Simulated Annealing

Cites work

• scientific article; zbMATH DE number 5544465 (Why is no real title available?)
• scientific article; zbMATH DE number 3745547 (Why is no real title available?)
• scientific article; zbMATH DE number 1153603 (Why is no real title available?)
• scientific article; zbMATH DE number 1889829 (Why is no real title available?)
• scientific article; zbMATH DE number 1413936 (Why is no real title available?)
• scientific article; zbMATH DE number 3063387 (Why is no real title available?)
• A Bernstein-type inequality for some mixing processes and dynamical systems with an application to learning
• A General Framework for Updating Belief Distributions
• A Relativised Variational Principle for Continuous Transformations
• A Variational Approach to Nonlinear Estimation
• About the posterior distribution in hidden Markov models with unknown number of states
• An Introduction to Symbolic Dynamics and Coding
• An introduction to joinings in ergodic theory
• Bayesian nonparametrics
• Bayesian variable selection in structured high-dimensional covariate spaces with applications in genomics
• Beneath the noise, chaos
• Consistency of Bayes estimates for nonparametric regression: normal theory
• Consistency of maximum likelihood estimation for some dynamical systems
• Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise
• Data Assimilation
• Denoising deterministic time series
• Disjointness in ergodic theory, minimal sets, and a problem in diophantine approximation
• Dynamics of Bayesian updating with dependent data and misspecified models
• Empirical risk minimization and complexity of dynamical models
• Empirical risk minimization for dynamical systems and stationary processes
• Equilibrium stability for non-uniformly hyperbolic systems
• Equilibrium states and the ergodic theory of Anosov diffeomorphisms
• Fast rates for general unbounded loss functions: from ERM to generalized Bayes
• From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion
• Fundamentals of nonparametric Bayesian inference
• Gaussian approximations for transition paths in Brownian dynamics
• Gibbs posterior for variable selection in high-dimensional classification and data mining
• Inconsistency of Bayesian inference for misspecified linear models, and a proposal for repairing it
• Information-theoretic upper and lower bounds for statistical estimation
• Minimax-optimal nonparametric regression in high dimensions
• On Bayes procedures
• On some recent advances on high dimensional Bayesian statistics
• On the consistency of Bayes estimates
• On the topological pressure for random bundle transformations.
• Posterior consistency for nonparametric hidden Markov models with finite state space
• Posterior consistency for partially observed Markov models
• Prior Probabilities
• Random dynamics
• Recurrence times and rates of mixing
• Relative Pressure, Relative Equilibrium States, Compensation Functions and Many-to-One Codes Between Subshifts
• Relative entropy and identification of Gibbs measures in dynamical systems
• Robust Bayesian inference via coarsening
• Scalable Bayesian inference for the inverse temperature of a hidden Potts model
• Some Large Deviation Results for Dynamical Systems
• Some PAC-Bayesian theorems
• Statistical inference for dynamical systems: a review
• Statistical properties of dynamical systems with some hyperbolicity
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Thermodynamic Formalism
• Variational Bayes and a problem of reliable communication. I: Finite systems

Cited in

(6)

• 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
• Bayes posterior convergence for loss functions via almost additive thermodynamic formalism
• The generalized IFS Bayesian method and an associated variational principle covering the classical and dynamical cases
• Gibbs' paradox and non-uniform convergence
• scientific article; zbMATH DE number 7625198 (Why is no real title available?)

This page was built for publication: Gibbs posterior convergence and the thermodynamic formalism

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117451)