Gibbs posterior convergence and the thermodynamic formalism

DOI10.1214/21-AAP1685zbMATH Open1493.62510arXiv1901.08641OpenAlexW2913067311MaRDI QIDQ2117451FDOQ2117451

Kevin McGoff, Sayan Mukherjee, Andrew B. Nobel

Publication date: 21 March 2022

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

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.

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)

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?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Scalable Bayesian inference for the inverse temperature of a hidden Potts model
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Fundamentals of Nonparametric Bayesian Inference
• On the consistency of Bayes estimates
• Minimax-optimal nonparametric regression in high dimensions
• Inconsistency of Bayesian inference for misspecified linear models, and a proposal for repairing it
• Robust Bayesian Inference via Coarsening
• A General Framework for Updating Belief Distributions
• Statistical properties of dynamical systems with some hyperbolicity
• Consistency of Bayes estimates for nonparametric regression: normal theory
• Recurrence times and rates of mixing
• Thermodynamic Formalism
• An Introduction to Symbolic Dynamics and Coding
• Disjointness in ergodic theory, minimal sets, and a problem in diophantine approximation
• Equilibrium states and the ergodic theory of Anosov diffeomorphisms
• Relative entropy and identification of Gibbs measures in dynamical systems
• Bayesian nonparametrics
• A Relativised Variational Principle for Continuous Transformations
• Some Large Deviation Results for Dynamical Systems
• Gibbs posterior for variable selection in high-dimensional classification and data mining
• Dynamics of Bayesian updating with dependent data and misspecified models
• An introduction to joinings in ergodic theory
• On Bayes procedures
• Prior Probabilities
• About the posterior distribution in hidden Markov models with unknown number of states
• Bayesian Variable Selection in Structured High-Dimensional Covariate Spaces With Applications in Genomics
• A Variational Approach to Nonlinear Estimation
• Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise
• A Bernstein-type inequality for some mixing processes and dynamical systems with an application to learning
• Some PAC-Bayesian theorems
• From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion
• Denoising deterministic time series
• Variational Bayes and a problem of reliable communication. I: Finite systems
• Relative Pressure, Relative Equilibrium States, Compensation Functions and Many-to-One Codes Between Subshifts
• Beneath the noise, chaos
• Data Assimilation
• Consistency of maximum likelihood estimation for some dynamical systems
• Statistical inference for dynamical systems: a review
• Information-theoretic upper and lower bounds for statistical estimation
• Equilibrium stability for non-uniformly hyperbolic systems
• 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
• Empirical risk minimization and complexity of dynamical models
• On some recent advances on high dimensional Bayesian statistics
• Empirical risk minimization for dynamical systems and stationary processes
• Gaussian Approximations for Transition Paths in Brownian Dynamics

Cited In (4)

• Dynamical hypothesis tests and decision theory for Gibbs distributions
• Decision theory and large deviations for dynamical hypotheses tests: the Neyman-Pearson lemma, min-max and Bayesian tests
• Gibbs' paradox and non-uniform convergence
• Title not available (Why is that?)

Recommendations

• Title not available (Why is that?) 👍 👎
• Thermodynamic integration and steppingstone sampling methods for estimating Bayes factors: a tutorial 👍 👎
• Estimating Bayes factors via thermodynamic integration and population MCMC 👍 👎
• Convergence of Gibbs Measures Associated with Simulated Annealing 👍 👎
• Gibbs sampling, conjugate priors and coupling 👍 👎
• On the properties of variational approximations of Gibbs posteriors 👍 👎
• Bayesian approach to thermostatistics 👍 👎
• Thermodynamic Bayesian model comparison 👍 👎
• Bayes posterior convergence for loss functions via almost additive thermodynamic formalism 👍 👎

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)