Back to search

Georgia Institute of Technology

ON SCALABLE AND FAST LANGEVIN-DYNAMICS-BASED SAMPLING ALGORITHMS

Abstract

dc:description.abstract

Langevin dynamics-based sampling algorithms are arguably among the most widelyused Markov Chain Monte Carlo (MCMC) methods. Two main directions of the modern study of MCMC methods are (i) How to scale MCMC methods to big data applications, and (ii) Tight convergence analysis of MCMC algorithms, with explicit dependence on various characteristics of target distribution, in a non-asymptotic manner. This thesis continues the previous efforts in this two lines and consists of three parts. In the first part, we study stochastic gradient MCMC methods for large scale application. We propose a non-uniform subsampling of gradients scheme to approximately match the transition kernel of a base MCMC base with full gradient, aiming for better sample quality. The demonstration is based on underdamped Langevin dynamics. In the second part, we consider an analog of Nesterov’s accelerated algorithm in optimization for sampling. We derive a dynamics termed Hessian-Free-High-Resolution (HFHR) dynamics, from a high-resolution ordinary differential equation description of the Nesterov’s accelerated algorithm. We then quantify the acceleration of HFHR over underdamped Langevin dynamics at both continuous dynamics level and discrete algorithm level. In the third part, we study a broad family of bounded, contractive-SDE-based sampling algorithms via mean-square analysis. We show how to extend the applicability of classical mean-square analysis from finite time to infinite time. Iteration complexity in 2-Wasserstein distance is also characterized and when applied to Langevin Monte Carlo algorithm, we obtain an improved iteration complexity bound.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Mathematics
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2021

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Li, Ruilin
Advisors dc:contributor.advisor
  • Zha, Hongyuan
  • Zhou, Haomin
Committee members dc:contributor.committeemember
  • Tao, Molei
  • Ye, Xiaojing
  • Mao, Cheng

Subjects

dc:subject × 1

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/64731

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Li, Ruilin. ON SCALABLE AND FAST LANGEVIN-DYNAMICS-BASED SAMPLING ALGORITHMS. Doctoral thesis, Georgia Institute of Technology, 2021. http://hdl.handle.net/1853/64731