Pith. sign in

REVIEW 1 cited by

Wide stochastic networks: Gaussian limit and PAC-Bayesian training

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 2106.09798 v3 pith:ZOCJ6WRX submitted 2021-06-17 stat.ML cs.LG

Wide stochastic networks: Gaussian limit and PAC-Bayesian training

classification stat.ML cs.LG
keywords trainingpac-bayesianallowsgaussianlargelimitnetworknetworks
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The limit of infinite width allows for substantial simplifications in the analytical study of over-parameterised neural networks. With a suitable random initialisation, an extremely large network exhibits an approximately Gaussian behaviour. In the present work, we establish a similar result for a simple stochastic architecture whose parameters are random variables, holding both before and during training. The explicit evaluation of the output distribution allows for a PAC-Bayesian training procedure that directly optimises the generalisation bound. For a large but finite-width network, we show empirically on MNIST that this training approach can outperform standard PAC-Bayesian methods.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. On the Induced Norms of Matrices and Grothendieck problems

    math.OC 2026-05 unverdicted novelty 5.0

    Analytic framework yields exact induced norms ||A||_{q→r} for key matrix classes and exact values for associated Grothendieck problems.