Back to search

University of British Columbia

Asymptotically exact variational inference via measure-preserving dynamical systems

Abstract

dc:description

Variational inference (VI) approximates a target distribution with a surrogate distribution within a pre-specified variational family designed to allow \iid sampling and density evaluation. The approximation is obtained by minimizing a divergence to the target, so its max obtainable quality is fundamentally determined by the expressiveness of the family. However, greater flexibility does not guarantee better approximations: the optimization problem is typically highly non-convex, making the theoretical optimum rarely attainable in practice. As a result, VI lacks the asymptotic exactness of Markov chain Monte Carlo methods (MCMC)---the guarantee of arbitrarily accurate inference results given sufficient computation regardless of tuning. This thesis addresses this limitation by introducing mixed variational flows (MixFlows), a framework for constructing practical, asymptotically exact variational families using measure-preserving dynamical systems. We develop both homogeneous MixFlows, derived from ergodic deterministic dynamics, and more general MixFlows, based on measure-preserving stochastic dynamics obtained from involutive MCMC kernels. We establish rigorous guarantees showing that every distribution in a MixFlow family converges in total variation to the target as the flow length increases, while retaining tractable density evaluation and i.i.d. sampling. A range of numerical examples illustrates these theoretical and methodological contributions. Along the way, we develop tools to analyze how probabilistic error propagates through inexact flow dynamics. Such inexactness may arise from floating-point computation or discretization of continuous-time flows. While the error of a single flow map may be negligible, composing many maps can cause severe accumulation. Surprisingly, we show empirically that flow-based inference often remains accurate despite instability. Drawing on shadowing theory from chaotic dynamical systems, we prove that errors in sampling, density evaluation, and evidence lower bound estimation grow far more slowly than trajectory errors themselves, which often grow exponentially with flow length.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy - PhD
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Statistics
Grantor dc:publisher
University of British Columbia
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Xu, Zuheng
Contributors dc:contributor
  • Campbell, Trevor (Professor of statistics)

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/93262

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Xu, Zuheng. Asymptotically exact variational inference via measure-preserving dynamical systems. doctoral thesis, University of British Columbia, 2025. http://hdl.handle.net/2429/93262