Pith. sign in

REVIEW 1 cited by

A Surprising Linear Relationship Predicts Test Performance 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 1807.09659 v1 pith:ON2NC7OP submitted 2018-07-25 cs.LG cs.AIcs.CVstat.ML

classification cs.LGcs.AIcs.CVstat.ML
keywords lossnetworkstestdifferentsametrainingcross-entropygeneralization
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalization may improve practical applications of deep networks. In this paper we show that with cross-entropy loss it is surprisingly simple to induce significantly different generalization performances for two networks that have the same architecture, the same meta parameters and the same training error: one can either pretrain the networks with different levels of "corrupted" data or simply initialize the networks with weights of different Gaussian standard deviations. A corollary of recent theoretical results on overfitting shows that these effects are due to an intrinsic problem of measuring test performance with a cross-entropy/exponential-type loss, which can be decomposed into two components both minimized by SGD -- one of which is not related to expected classification performance. However, if we factor out this component of the loss, a linear relationship emerges between training and test losses. Under this transformation, classical generalization bounds are surprisingly tight: the empirical/training loss is very close to the expected/test loss. Furthermore, the empirical relation between classification error and normalized cross-entropy loss seem to be approximately monotonic

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. Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization

    cs.LG 2019-08 conditional novelty 3.0 of 10

    A synthesis of approximation, optimization, and generalization theory arguing that gradient descent's implicit norm control on weight directions explains why overparameterized deep networks generalize.

Pith tools