Papers › Variational Bayesian Neural Networks via Resolution of Singularities

Variational Bayesian Neural Networks via Resolution of Singularities

13 Feb 2023arXiv:2302.06035archive 2025-07-28

Susan Wei, Edmund Lau

In this work, we advocate for the importance of singular learning theory (SLT) as it pertains to the theory and practice of variational inference in Bayesian neural networks (BNNs). To begin, using SLT, we lay to rest some of the confusion surrounding discrepancies between downstream predictive performance measured via e.g., the test log predictive density, and the variational objective. Next, we use the SLT-corrected asymptotic form for singular posterior distributions to inform the design of the variational family itself. Specifically, we build upon the idealized variational family introduced in \citet{bhattacharya_evidence_2020} which is theoretically appealing but practically intractable. Our proposal takes shape as a normalizing flow where the base distribution is a carefully-initialized generalized gamma. We conduct experiments comparing this to the canonical Gaussian base distribution and show improvements in terms of variational free energy and variational generalization error.

PaperPDFCode

Code

suswei/bnn_via_slt officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Learning TheoryVariational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASETestVariational Inference

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections