The geometric foundations of Hamiltonian Monte Carlo

DOI10.3150/16-BEJ810zbMath1380.60070arXiv1410.5110OpenAlexW2962703949MaRDI QIDQ2405109

Simon Byrne, Sam Livingstone, Michael Betancourt, Mark A. Girolami

Publication date: 21 September 2017

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1410.5110

zbMATH Keywords

Riemannian geometrysymplectic geometryMarkov chain Monte Carlodifferential geometryfiber bundledisintegrationHamiltonian Monte Carlosmooth manifold

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Global differential geometry (53C99)

Related Items (27)

Stochastic approximation Hamiltonian Monte Carlo ⋮ Stochastic gradient Hamiltonian Monte Carlo for non-convex learning ⋮ Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration ⋮ Coupling and convergence for Hamiltonian Monte Carlo ⋮ A comparative study on the performance of frequentist and Bayesian estimation methods under separation in logistic regression ⋮ The Convergence of Markov Chain Monte Carlo Methods: From the Metropolis Method to Hamiltonian Monte Carlo ⋮ Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems ⋮ Geometry and applied statistics ⋮ Bregman dynamics, contact transformations and convex optimization ⋮ Adaptive tuning of Hamiltonian Monte Carlo within sequential Monte Carlo ⋮ Modified Cholesky Riemann manifold Hamiltonian Monte Carlo: exploiting sparsity for fast sampling of high-dimensional targets ⋮ Staying the course: iteratively locating equilibria of dynamical systems on Riemannian manifolds defined by point-clouds ⋮ Bayesian differential programming for robust systems identification under uncertainty ⋮ Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo ⋮ An approach to stability analyses in general relativity via symplectic geometry ⋮ Emulation of higher-order tensors in manifold Monte Carlo methods for Bayesian inverse problems ⋮ Bayesian computation: a summary of the current state, and samples backwards and forwards ⋮ Modified Hamiltonian Monte Carlo for Bayesian inference ⋮ Ranking with Hamiltonian dynamics ⋮ On the geometric ergodicity of Hamiltonian Monte Carlo ⋮ Hybrid Monte Carlo methods for sampling probability measures on submanifolds ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice ⋮ Normal-Bundle Bootstrap ⋮ Hamiltonian Monte Carlo with explicit, reversible, and volume-preserving adaptive step size control ⋮ Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions ⋮ Geometric Integration of Measure-Preserving Flows for Sampling ⋮ Estimation methods for stationary Gegenbauer processes

This page was built for publication: The geometric foundations of Hamiltonian Monte Carlo