Score: 0

Walking on the Fiber: A Simple Geometric Approximation for Bayesian Neural Networks

Published: December 1, 2025 | arXiv ID: 2512.01500v1

By: Alfredo Reichlin, Miguel Vasco, Danica Kragic

Potential Business Impact:

Lets computers learn with less guessing.

Business Areas:
A/B Testing Data and Analytics

Bayesian Neural Networks provide a principled framework for uncertainty quantification by modeling the posterior distribution of network parameters. However, exact posterior inference is computationally intractable, and widely used approximations like the Laplace method struggle with scalability and posterior accuracy in modern deep networks. In this work, we revisit sampling techniques for posterior exploration, proposing a simple variation tailored to efficiently sample from the posterior in over-parameterized networks by leveraging the low-dimensional structure of loss minima. Building on this, we introduce a model that learns a deformation of the parameter space, enabling rapid posterior sampling without requiring iterative methods. Empirical results demonstrate that our approach achieves competitive posterior approximations with improved scalability compared to recent refinement techniques. These contributions provide a practical alternative for Bayesian inference in deep learning.

Country of Origin
πŸ‡ΈπŸ‡ͺ Sweden

Page Count
22 pages

Category
Computer Science:
Machine Learning (CS)