Even More Guarantees for Variational Inference in the Presence of Symmetries

arXiv:2604.21407v1 Announce Type: new Abstract: 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 alpha-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 alpha-value.

Related

• Symmetry Guarantees Statistic Recovery in Variational Inference
• Resource-efficient equivariant quantum convolutional neural networks
• Trainability Beyond Linearity in Variational Quantum Objectives
• Efficient Autoregressive Inference for Transformer Probabilistic Models
• Reachability Constraints in Variational Quantum Circuits: Optimization within Polynomial Group Module

Source: arXiv cs.LG | 2026-04-24