1 code implementation • 23 Apr 2024 • Nawaf Bou-Rabee, Bob Carpenter, Milo Marsden
We present a novel and flexible framework for localized tuning of Hamiltonian Monte Carlo samplers by sampling the algorithm's tuning parameters conditionally based on the position and momentum at each step.
no code implementations • 11 Oct 2023 • Nawaf Bou-Rabee, Tore Selland Kleppe
We present 5/2- and 7/2-order $L^2$-accurate randomized Runge-Kutta-Nystr\"om methods to approximate the Hamiltonian flow underlying various non-reversible Markov chain Monte Carlo chains including unadjusted Hamiltonian Monte Carlo and unadjusted kinetic Langevin chains.
no code implementations • 20 Nov 2022 • Nawaf Bou-Rabee, Milo Marsden
A novel randomized time integrator is suggested for unadjusted Hamiltonian Monte Carlo (uHMC) in place of the usual Verlet integrator; namely, a stratified Monte Carlo (sMC) integrator which involves a minor modification to Verlet, and hence, is easy to implement.
no code implementations • 3 May 2021 • Nawaf Bou-Rabee, Andreas Eberle
We provide quantitative upper bounds on the total variation mixing time of the Markov chain corresponding to the unadjusted Hamiltonian Monte Carlo (uHMC) algorithm.
no code implementations • 29 Sep 2020 • Nawaf Bou-Rabee, Andreas Eberle
Andersen dynamics is a standard method for molecular simulations, and a precursor of the Hamiltonian Monte Carlo algorithm used in MCMC inference.
no code implementations • 1 May 2018 • Nawaf Bou-Rabee, Andreas Eberle, Raphael Zimmer
Based on a new coupling approach, we prove that the transition step of the Hamiltonian Monte Carlo algorithm is contractive w. r. t.
1 code implementation • 14 Nov 2017 • Nawaf Bou-Rabee, Jesús María Sanz-Serna
This paper surveys in detail the relations between numerical integration and the Hamiltonian (or hybrid) Monte Carlo method (HMC).
Probability Numerical Analysis Computation Methodology
no code implementations • 16 Aug 2007 • Nawaf Bou-Rabee, Houman Owhadi
This paper presents a continuous and discrete Lagrangian theory for stochastic Hamiltonian systems on manifolds.
Probability 65Cxx; 37Jxx