paper-with-me

홈 › Papers

Convergence Rate of Riemannian Hamiltonian Monte Carlo and Faster Polytope Volume Computation

2017-10-17 · Yin Tat Lee, Santosh S. Vempala

We give the first rigorous proof of the convergence of Riemannian Hamiltonian Monte Carlo, a general (and practical) method for sampling Gibbs distributions. Our analysis shows that the rate of convergence is bounded in terms of natural smoothness parameters of an associated Riemannian manifold. We then apply the method with the manifold defined by the log barrier function to the problems of (1) uniformly sampling a polytope and (2) computing its volume, the latter by extending Gaussian cooling to the manifold setting. In both cases, the total number of steps needed is O^{*}(mn^{\frac{2}{3}}), improving the state of the art. A key ingredient of our analysis is a proof of an analog of the KLS conjecture for Gibbs distributions over manifolds.

📄 PDF Abstract BibTeX arXiv:1710.06261

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Antithetic Riemannian Manifold And Quantum-Inspired Hamiltonian Monte Carlo

2021-07-05 · Wilson Tsakane Mongwe, Rendani Mbuvha, Tshilidzi Marwala

Markov Chain Monte Carlo inference of target posterior distributions in machine learning is predominately conducted via Hamiltonian Monte Carlo and its variants. This is due to Hamiltonian Monte Carlo based samplers abil…

Introducing an Explicit Symplectic Integration Scheme for Riemannian Manifold Hamiltonian Monte Carlo

2019-10-14 · Adam D. Cobb, Atılım Güneş Baydin, Andrew Markham, Stephen J. Roberts

We introduce a recent symplectic integration scheme derived for solving physically motivated systems with non-separable Hamiltonians. We show its relevance to Riemannian manifold Hamiltonian Monte Carlo (RMHMC) and provi…

Bayesian Inference

Condition-number-independent convergence rate of Riemannian Hamiltonian Monte Carlo with numerical integrators

2022-10-13 · Yunbum Kook, Yin Tat Lee, Ruoqi Shen, Santosh S. Vempala

We study the convergence rate of discretized Riemannian Hamiltonian Monte Carlo on sampling from distributions in the form of $e^{-f(x)}$ on a convex body $\mathcal{M}\subset\mathbb{R}^{n}$. We show that for distribution…

Form

An Efficient Implementation of Riemannian Manifold Hamiltonian Monte Carlo for Gaussian Process Models

2018-10-28 · Ulrich Paquet, Marco Fraccaro

This technical report presents pseudo-code for a Riemannian manifold Hamiltonian Monte Carlo (RMHMC) method to efficiently simulate samples from $N$-dimensional posterior distributions $p(x|y)$, where $x \in R^N$ is draw…

Geometric Ergodicity in Modified Variations of Riemannian Manifold and Lagrangian Monte Carlo

2023-01-04 · James A. Brofos, Vivekananda Roy, Roy R. Lederman

Riemannian manifold Hamiltonian (RMHMC) and Lagrangian Monte Carlo (LMC) have emerged as powerful methods of Bayesian inference. Unlike Euclidean Hamiltonian Monte Carlo (EHMC) and the Metropolis-adjusted Langevin algori…

Bayesian Inference