Convergence rate of Riemannian Hamiltonian Monte Carlo and faster polytope volume computation

DOI10.1145/3188745.3188774zbMath1429.65009arXiv1710.06261OpenAlexW2963559717MaRDI QIDQ5230366

Yin Tat Lee, Santosh Vempala

Publication date: 22 August 2019

Published in: Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1710.06261

zbMATH Keywords

samplingpolytopesHamiltonian dynamicsvolume computation

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18) Complexity and performance of numerical algorithms (65Y20)

Related Items (12)

On the mixing time of coordinate Hit-and-Run ⋮ Efficient sampling in spectrahedra and volume approximation ⋮ Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Randomized time Riemannian manifold Hamiltonian Monte Carlo ⋮ Simulating Coulomb and log-gases with hybrid Monte Carlo algorithms ⋮ High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion ⋮ Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Mixing time guarantees for unadjusted Hamiltonian Monte Carlo

This page was built for publication: Convergence rate of Riemannian Hamiltonian Monte Carlo and faster polytope volume computation