Pith. sign in

REVIEW 1 cited by

Theory IIIb: Generalization in Deep 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 1806.11379 v1 pith:6M7AEYG2 submitted 2018-06-29 cs.LG cs.AIcs.NEstat.ML

classification cs.LGcs.AIcs.NEstat.ML
keywords lossdeepdnnsnetworksprovesolutionabsencedescent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A main puzzle of deep neural networks (DNNs) revolves around the apparent absence of "overfitting", defined in this paper as follows: the expected error does not get worse when increasing the number of neurons or of iterations of gradient descent. This is surprising because of the large capacity demonstrated by DNNs to fit randomly labeled data and the absence of explicit regularization. Recent results by Srebro et al. provide a satisfying solution of the puzzle for linear networks used in binary classification. They prove that minimization of loss functions such as the logistic, the cross-entropy and the exp-loss yields asymptotic, "slow" convergence to the maximum margin solution for linearly separable datasets, independently of the initial conditions. Here we prove a similar result for nonlinear multilayer DNNs near zero minima of the empirical loss. The result holds for exponential-type losses but not for the square loss. In particular, we prove that the weight matrix at each layer of a deep network converges to a minimum norm solution up to a scale factor (in the separable case). Our analysis of the dynamical system corresponding to gradient descent of a multilayer network suggests a simple criterion for ranking the generalization performance of different zero minimizers of the empirical loss.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Can Bayesian Neural Networks Make Confident Predictions?

    stat.ML 2025-01 reject novelty 5.0 of 10

    Under a discrete hidden-layer prior, a Bayesian neural network's predictive distribution is a Gaussian mixture, and parameters with identical training error can produce distinct predictive modes, so unimodal approxima...

Pith tools