Back to search

Georgia Institute of Technology

Learning, sampling and inference with stochastic differential equations

Abstract

dc:description.abstract

Stochastic differential equations (SDEs) constitute a formidable tool for modeling the dynamics of continuous-time stochastic processes, and offer a natural framework for the probabilistic modeling of high-dimensional data. Consequently, they have garnered increasing attention in generative machine learning. Despite their promise, the applications of SDEs in machine learning have been limited due to the lack of scalable learning approaches that can train flexible neural networks to approximate stochastic processes, and the difficulty of conducting tractable inference and sampling caused by inefficient SDE solvers. In this dissertation, I outline my efforts to develop novel computational models capable of efficient and scalable learning, sampling, and inference from SDEs. Specifically, I introduce several approaches to learning SDEs for probabilistic modeling, including fitting non-linear forward and backward SDEs with neural networks and learning with limited data. Next, I present a novel deep model designed to learn SDE dynamics while satisfying given constraints on the marginal probability of the SDE. Furthermore, I develop an efficient algorithm for drawing samples from high-dimensional SDEs, which proves effective in generating diverse and high-fidelity data, such as realistic images and videos.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Aerospace Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhang, Qinsheng
Advisor dc:contributor.advisor
  • Chen, Yongxin
Committee members dc:contributor.committeemember
  • Tao, Molei
  • Xu, Danfei
  • Shi, Humphrey
  • Kira, Zsolt

Subjects

dc:subject × 3

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/73161

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

Zhang, Qinsheng. Learning, sampling and inference with stochastic differential equations. Doctoral thesis, Georgia Institute of Technology, 2023. https://hdl.handle.net/1853/73161