Pith. sign in

REVIEW 2 cited by

Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear 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 1703.02930 v3 pith:OAGOQ5JS submitted 2017-03-08 cs.LG

classification cs.LG
keywords boundsvc-dimensiondependencelinearnetworksnumberproveactivation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

We prove new upper and lower bounds on the VC-dimension of deep neural networks with the ReLU activation function. These bounds are tight for almost the entire range of parameters. Letting $W$ be the number of weights and $L$ be the number of layers, we prove that the VC-dimension is $O(W L \log(W))$, and provide examples with VC-dimension $\Omega( W L \log(W/L) )$. This improves both the previously known upper bounds and lower bounds. In terms of the number $U$ of non-linear units, we prove a tight bound $\Theta(W U)$ on the VC-dimension. All of these bounds generalize to arbitrary piecewise linear activation functions, and also hold for the pseudodimensions of these function classes. Combined with previous results, this gives an intriguing range of dependencies of the VC-dimension on depth for networks with different non-linearities: there is no dependence for piecewise-constant, linear dependence for piecewise-linear, and no more than quadratic dependence for general piecewise-polynomial.

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. CNN-ViT Hybrid for Pneumonia Detection: Theory and Empiric on Limited Data without Pretraining

    eess.IV 2025-09 conditional novelty 4.0 of 10

    A from-scratch CNN-ViT hybrid outperformed standalone CNN and ViT on limited and imbalanced pneumonia chest X-ray data, achieving 0.9443 recall at 50% data and F1 around 0.85.

  2. A Probabilistic Representation of Deep Learning

    cs.LG 2019-08 reject novelty 3.0 of 10

    Deep neural networks can be represented as Bayesian hierarchical models built from neuron-defined Gibbs distributions, yielding a new explanation of regularization and generalization.

Pith tools