On Convergence of the Alternating Directions SGHMC Algorithm

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ghosh, Soumyadip, Lu, Yingdong, Nowicki, Tomasz
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929358992572416
author Ghosh, Soumyadip
Lu, Yingdong
Nowicki, Tomasz
author_facet Ghosh, Soumyadip
Lu, Yingdong
Nowicki, Tomasz
contents We study convergence rates of Hamiltonian Monte Carlo (HMC) algorithms with leapfrog integration under mild conditions on stochastic gradient oracle for the target distribution (SGHMC). Our method extends standard HMC by allowing the use of general auxiliary distributions, which is achieved by a novel procedure of Alternating Directions. The convergence analysis is based on the investigations of the Dirichlet forms associated with the underlying Markov chain driving the algorithms. For this purpose, we provide a detailed analysis on the error of the leapfrog integrator for Hamiltonian motions with both the kinetic and potential energy functions in general form. We characterize the explicit dependence of the convergence rates on key parameters such as the problem dimension, functional properties of both the target and auxiliary distributions, and the quality of the oracle.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13140
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On Convergence of the Alternating Directions SGHMC Algorithm
Ghosh, Soumyadip
Lu, Yingdong
Nowicki, Tomasz
Statistics Theory
Machine Learning
Probability
We study convergence rates of Hamiltonian Monte Carlo (HMC) algorithms with leapfrog integration under mild conditions on stochastic gradient oracle for the target distribution (SGHMC). Our method extends standard HMC by allowing the use of general auxiliary distributions, which is achieved by a novel procedure of Alternating Directions. The convergence analysis is based on the investigations of the Dirichlet forms associated with the underlying Markov chain driving the algorithms. For this purpose, we provide a detailed analysis on the error of the leapfrog integrator for Hamiltonian motions with both the kinetic and potential energy functions in general form. We characterize the explicit dependence of the convergence rates on key parameters such as the problem dimension, functional properties of both the target and auxiliary distributions, and the quality of the oracle.
title On Convergence of the Alternating Directions SGHMC Algorithm
topic Statistics Theory
Machine Learning
Probability
url https://arxiv.org/abs/2405.13140