Even More Guarantees for Variational Inference in the Presence of Symmetries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zellinger, Lena, Vergari, Antonio
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915951685926912
author Zellinger, Lena
Vergari, Antonio
author_facet Zellinger, Lena
Vergari, Antonio
contents When approximating an intractable density via variational inference (VI) the variational family is typically chosen as a simple parametric family that very likely does not contain the target. This raises the question: Under which conditions can we recover characteristics of the target despite misspecification? In this work, we extend previous results on robust VI with location-scale families under target symmetries. We derive sufficient conditions guaranteeing exact recovery of the mean when using the forward Kullback-Leibler divergence and $α$-divergences. We further show how and why optimization can fail to recover the target mean in the absence of our sufficient conditions, providing initial guidelines on the choice of the variational family and $α$-value.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21407
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Even More Guarantees for Variational Inference in the Presence of Symmetries
Zellinger, Lena
Vergari, Antonio
Machine Learning
Computation
When approximating an intractable density via variational inference (VI) the variational family is typically chosen as a simple parametric family that very likely does not contain the target. This raises the question: Under which conditions can we recover characteristics of the target despite misspecification? In this work, we extend previous results on robust VI with location-scale families under target symmetries. We derive sufficient conditions guaranteeing exact recovery of the mean when using the forward Kullback-Leibler divergence and $α$-divergences. We further show how and why optimization can fail to recover the target mean in the absence of our sufficient conditions, providing initial guidelines on the choice of the variational family and $α$-value.
title Even More Guarantees for Variational Inference in the Presence of Symmetries
topic Machine Learning
Computation
url https://arxiv.org/abs/2604.21407