Information-geometric Markov chain Monte Carlo methods using diffusions

DOI10.3390/e16063074zbMath1338.65018arXiv1403.7957OpenAlexW3102676823MaRDI QIDQ296467

Samuel Livingstone, Mark A. Girolami

Publication date: 15 June 2016

Published in: Entropy (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1403.7957

zbMATH Keywords

Markov chain Monte Carlodiffusionsstatistical mechanicsinformation geometryBayesian inferencemachine learningcomputational statistics

Mathematics Subject Classification ID

Directional data; spatial statistics (62H11) Computational methods in Markov chains (60J22) Discrete-time Markov processes on general state spaces (60J05) Numerical analysis or methods applied to Markov chains (65C40) Diffusion processes and stochastic analysis on manifolds (58J65) Statistical aspects of information-theoretic topics (62B10) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70)

Related Items (11)

Asymptotic analysis of the random walk metropolis algorithm on ridged densities ⋮ Markov Kernels Local Aggregation for Noise Vanishing Distribution Sampling ⋮ Computing with Fisher geodesics and extended exponential families ⋮ Convergence of Position-Dependent MALA with Application to Conditional Simulation in GLMMs ⋮ A fresh Take on ‘Barker Dynamics’ for MCMC ⋮ Affine Invariant Interacting Langevin Dynamics for Bayesian Inference ⋮ Adaptive Step Size Selection for Hessian-Based Manifold Langevin Samplers ⋮ Geometric adaptive Monte Carlo in random environment ⋮ On the geometric ergodicity of Hamiltonian Monte Carlo ⋮ Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics ⋮ Geometric Integration of Measure-Preserving Flows for Sampling

Uses Software

• R
• CODA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Computing the nearest correlation matrix--a problem from finance
• Optimal scaling of the random walk Metropolis on elliptically symmetric unimodal targets
• The imbedding problem for Riemannian manifolds
• The random walk Metropolis: linking theory and practice through a case study
• Optimal scaling for random walk Metropolis on spherically constrained target densities
• On the Markov chain central limit theorem
• Central limit theorem for additive functionals of reversible Markov processes and applications to simple exclusions
• Preferred point geometry and statistical manifolds
• Exponential convergence of Langevin distributions and their discrete approximations
• Langevin diffusions and Metropolis-Hastings algorithms
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Optimal scaling for various Metropolis-Hastings algorithms.
• Necessary conditions for geometric and polynomial ergodicity of random-walk-type Markov chains
• Geometric ergodicity of Metropolis algorithms
• Inference from iterative simulation using multiple sequences
• Markov chains for exploring posterior distributions. (With discussion)
• Rates of convergence of the Hastings and Metropolis algorithms
• Advanced MCMC methods for sampling on diffusion pathspace
• Proposals which speed up function-space MCMC
• Langevin diffusions and the Metropolis-adjusted Langevin algorithm
• Geodesic Monte Carlo on Embedded Manifolds
• A Stochastic Newton MCMC Method for Large-Scale Statistical Inverse Problems with Application to Seismic Inversion
• Markov chain Monte Carlo inference for Markov jump processes via the linear noise approximation
• Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
• The Role of Differential Geometry in Statistical Theory
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• Time-reversible diffusions
• Applications of Differential Geometry to Econometrics
• On the local geometry of mixture models
• On Choosing and Bounding Probability Metrics
• Optimal Scaling of the Random Walk Metropolis: General Criteria for the 0.234 Acceptance Rule
• An invariant form for the prior probability in estimation problems
• Geometric ergodicity of Metropolis-Hastings algorithms for conditional simulation in generalized linear mixed models
• MCMC methods for functions: modifying old algorithms to make them faster

This page was built for publication: Information-geometric Markov chain Monte Carlo methods using diffusions