Pith. sign in

REVIEW 2 cited by

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.09184 v2 pith:NOPIWB5C submitted 2022-11-16 stat.ML cs.LG

classification stat.MLcs.LG
keywords bnnsmodelbayesianfinite-finite-widthinfinite-widthnetworksneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width increases, multiple model properties change simultaneously, and, inference in the finite-width case is intractable. In this work, we empirically compare finite- and infinite-width BNNs, and provide quantitative and qualitative explanations for their performance difference. We find that when the model is mis-specified, increasing width can hurt BNN performance. In these cases, we provide evidence that finite-width BNNs generalize better partially due to the properties of their frequency spectrum that allows them to adapt under model mismatch.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation

    stat.ML 2025-10 conditional novelty 8.0 of 10

    A replica/HCIZ theory predicts the Bayes-optimal generalization error of proportional-width MLPs near interpolation and discovers layer-wise specialization transitions that make deeper targets harder to learn.

  2. A ZeNN architecture to avoid the Gaussian trap

    cs.LG 2025-05 conditional novelty 6.0 of 10

    ZeNNs, which replace the equal-weight average of MLP neurons with an index-weighted sum of frequency-scaled neurons, provably converge pointwise, retain non-Gaussian limits, and learn high-frequency features in low-di...

Pith tools