English

Beyond NNGP: Large Deviations and Feature Learning in Bayesian Neural Networks

Machine Learning 2026-02-27 v1 Machine Learning

Abstract

We study wide Bayesian neural networks focusing on the rare but statistically dominant fluctuations that govern posterior concentration, beyond Gaussian-process limits. Large-deviation theory provides explicit variational objectives-rate functions-on predictors, providing an emerging notion of complexity and feature learning directly at the functional level. We show that the posterior output rate function is obtained by a joint optimization over predictors and internal kernels, in contrast with fixed-kernel (NNGP) theory. Numerical experiments demonstrate that the resulting predictions accurately describe finite-width behavior for moderately sized networks, capturing non-Gaussian tails, posterior deformation, and data-dependent kernel selection effects.

Keywords

Cite

@article{arxiv.2602.22925,
  title  = {Beyond NNGP: Large Deviations and Feature Learning in Bayesian Neural Networks},
  author = {Katerina Papagiannouli and Dario Trevisan and Giuseppe Pio Zitto},
  journal= {arXiv preprint arXiv:2602.22925},
  year   = {2026}
}
R2 v1 2026-07-01T10:53:48.054Z