Symmetry Guarantees Statistic Recovery in Variational Inference

TL;DR

This paper develops a general theory explaining how symmetries in variational inference enable the recovery of certain statistics, providing new guarantees and a modular framework across various symmetry settings.

Contribution

It introduces a unified, problem-agnostic framework for understanding symmetry-induced statistic recovery in variational inference, extending existing results and applying to new distribution families.

Findings

Characterizes when variational minimisers inherit target symmetries.

Unifies existing statistic recovery guarantees in location-scale families.

Provides new guarantees for directional statistics on the sphere.

Abstract

Variational inference (VI) is a central tool in modern machine learning, used to approximate an intractable target density by optimising over a tractable family of distributions. As the variational family cannot typically represent the target exactly, guarantees on the quality of the resulting approximation are crucial for understanding which of its properties VI can faithfully capture. Recent work has identified instances in which symmetries of the target and the variational family enable the recovery of certain statistics, even under model misspecification. However, these guarantees are inherently problem-specific and offer little insight into the fundamental mechanism by which symmetry forces statistic recovery. In this paper, we overcome this limitation by developing a general theory of symmetry-induced statistic recovery in variational inference. First, we characterise when variational minimisers inherit the symmetries of the target and establish conditions under which these pin down identifiable statistics. Second, we unify existing results by showing that previously known statistic recovery guarantees in location-scale families arise as special cases of our theory. Third, we apply our framework to distributions on the sphere to obtain novel guarantees for directional statistics in von Mises-Fisher families. Together, these results provide a modular blueprint for deriving new recovery guarantees for VI in a broad range of symmetry settings.