Asymptotically exact variational flows via involutive MCMC kernels

Zuheng Xu, Trevor Campbell

Keywords: Bayesian, variational inference, MCMC, convergence

TL;DR: A general recipe for constructing tuning-free, asymptotically exact variational flows from general involutive MCMC kernels.

Abstract:

Most expressive variational families---such as normalizing flows---lack practical convergence guarantees,
as their theoretical assurances typically hold only at the intractable global optimum.
In this work, we present a general recipe for constructing tuning-free, asymptotically exact variational flows on *arbitrary* state
spaces from involutive MCMC kernels.
The core methodological component is a novel representation of general involutive MCMC kernels as invertible, measure-
preserving iterated random function systems, which act as the flow maps of our variational flows. This leads to three new variational families with provable total variation convergence. Our framework resolves key practical limitations of existing variational families with similar guarantees (e.g., MixFlows), while requiring substantially weaker theoretical assumptions. Finally, we demonstrate the competitive performance of our flows across tasks including posterior approximation, Monte Carlo estimates, and normalization constant estimation, outperforming or matching No-U-Turn sampler (NUTS) and black-box normalizing flows.

Primary Area: Probabilistic methods (e.g., variational inference, causal inference, Gaussian processes)

Submission Number: 8426