Bayesian nonparametric analysis of reversible Markov chains
From MaRDI portal
Abstract: We introduce a three-parameter random walk with reinforcement, called the scheme, which generalizes the linearly edge reinforced random walk to uncountable spaces. The parameter smoothly tunes the scheme between this edge reinforced random walk and the classical exchangeable two-parameter Hoppe urn scheme, while the parameters and modulate how many states are typically visited. Resorting to de Finetti's theorem for Markov chains, we use the scheme to define a nonparametric prior for Bayesian analysis of reversible Markov chains. The prior is applied in Bayesian nonparametric inference for species sampling problems with data generated from a reversible Markov chain with an unknown transition kernel. As a real example, we analyze data from molecular dynamics simulations of protein folding.
Recommendations
Cites work
- scientific article; zbMATH DE number 4161783 (Why is no real title available?)
- scientific article; zbMATH DE number 3669678 (Why is no real title available?)
- scientific article; zbMATH DE number 3443655 (Why is no real title available?)
- scientific article; zbMATH DE number 5021952 (Why is no real title available?)
- A Bayesian analysis of some nonparametric problems
- Bayesian Nonparametric Estimation of the Probability of Discovering New Species
- Bayesian analysis for reversible Markov chains
- Bayesian analysis of variable-order, reversible Markov chains
- Bayesian nonparametric analysis of reversible Markov chains
- De Finetti's theorem for Markov chains
- Edge-reinforced random walk on finite graphs
- Exact sampling with coupled Markov chains and applications to statistical mechanics
- Ferguson distributions via Polya urn schemes
- Gibbs Sampling Methods for Stick-Breaking Priors
- Hierarchical Dirichlet Processes
- Hierarchical reinforced urn processes
- How edge-reinforced random walk arises naturally
- Recurrence of edge-reinforced random walk on a two-dimensional graph
- The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator
- W. E. Johnson's sufficientness postulate
Cited in
(12)- Bayesian Inference in Hidden Markov Models Through the Reversible Jump Markov Chain Monte Carlo Method
- A note on nonparametric inference for species variety with Gibbs-type priors
- Approximating predictive probabilities of Gibbs-type priors
- Probabilistic symmetries and invariant neural networks
- Bayesian nonparametric analysis of reversible Markov chains
- Bayesian M-T clustering for reduced parameterisation of Markov chains used for nonlinear adaptive elements
- Bayesian analysis for reversible Markov chains
- Bayesian nonparametric inference for shared species richness in multiple populations
- Bayesian inversion by parallel interacting Markov chains
- Bayesian analysis of variable-order, reversible Markov chains
- Sufficientness postulates for Gibbs-type priors and hierarchical generalizations
- Forward-reverse expectation-maximization algorithm for Markov chains: convergence and numerical analysis
This page was built for publication: Bayesian nonparametric analysis of reversible Markov chains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q355117)