Improved discretization analysis for underdamped Langevin Monte Carlo
Abstract Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from
unnormalized densities by leveraging the momentum of a particle moving in a potential well …
unnormalized densities by leveraging the momentum of a particle moving in a potential well …
Unbiased kinetic Langevin Monte Carlo with inexact gradients
We present an unbiased method for Bayesian posterior means based on kinetic Langevin
dynamics that combines advanced splitting methods with enhanced gradient …
dynamics that combines advanced splitting methods with enhanced gradient …
Entropy contraction of the Gibbs sampler under log-concavity
The Gibbs sampler (aka Glauber dynamics and heat-bath algorithm) is a popular Markov
Chain Monte Carlo algorithm which iteratively samples from the conditional distributions of a …
Chain Monte Carlo algorithm which iteratively samples from the conditional distributions of a …
Minimal autocorrelation in hybrid Monte Carlo simulations using exact Fourier acceleration
J Ostmeyer, P Buividovich - arxiv preprint arxiv:2404.09723, 2024 - arxiv.org
The hybrid Monte Carlo (HMC) algorithm is a ubiquitous method in computational physics
with applications ranging from condensed matter to lattice QCD and beyond. However, HMC …
with applications ranging from condensed matter to lattice QCD and beyond. However, HMC …
Mixing of the No-U-Turn Sampler and the Geometry of Gaussian Concentration
We prove that the mixing time of the No-U-Turn Sampler (NUTS), when initialized in the
concentration region of the canonical Gaussian measure, scales as $ d^{1/4} $, up to …
concentration region of the canonical Gaussian measure, scales as $ d^{1/4} $, up to …
[HTML][HTML] EVCA classifier: a MCMC-based classifier for analyzing high-dimensional big data
In this work, we introduce an innovative Markov Chain Monte Carlo (MCMC) classifier, a
synergistic combination of Bayesian machine learning and Apache Spark, highlighting the …
synergistic combination of Bayesian machine learning and Apache Spark, highlighting the …
Tuning diagonal scale matrices for HMC
JH Tran, TS Kleppe - Statistics and Computing, 2024 - Springer
Three approaches for adaptively tuning diagonal scale matrices for HMC are discussed and
compared. The common practice of scaling according to estimated marginal standard …
compared. The common practice of scaling according to estimated marginal standard …
Is Gibbs sampling faster than Hamiltonian Monte Carlo on GLMs?
The Hamiltonian Monte Carlo (HMC) algorithm is often lauded for its ability to effectively
sample from high-dimensional distributions. In this paper we challenge the presumed …
sample from high-dimensional distributions. In this paper we challenge the presumed …
Kinetic Langevin Monte Carlo methods
PA Whalley - 2024 - era.ed.ac.uk
In this thesis, we study discretizations of kinetic Langevin dynamics within the context of
Markov chain Monte Carlo. We compare the convergence properties for different choices of …
Markov chain Monte Carlo. We compare the convergence properties for different choices of …
[PDF][PDF] UNBIASED KINETIC LANGEVIN MONTE CARLO WITH INEXACT GRADIENTS BY NEIL K. CHADA, BENEDICT LEIMKUHLER 2, b, DANIEL PAULIN 2, c AND …
NK CHADA - arxiv preprint arxiv:2311.05025, 2023 - researchgate.net
We present an unbiased method for Bayesian posterior means based on kinetic Langevin
dynamics that combines advanced splitting methods with enhanced gradient …
dynamics that combines advanced splitting methods with enhanced gradient …