Pith. sign in

REVIEW 4 cited by

Spectrally-normalized margin bounds for 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 1706.08498 v2 pith:2IDMEMU2 submitted 2017-06-26 cs.LG cs.NEstat.ML

classification cs.LGcs.NEstat.ML
keywords boundcomplexitylipschitznetworksneuralscalesspectralalexnet
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for a standard AlexNet network trained with SGD on the mnist and cifar10 datasets, with both original and random labels; the bound, the Lipschitz constants, and the excess risks are all in direct correlation, suggesting both that SGD selects predictors whose complexity scales with the difficulty of the learning task, and secondly that the presented bound is sensitive to this complexity.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 174 citations worldwide. Full citation record

  1. Nearly Optimal Strong Coresets for $\ell_p$ Subspace Approximation

    cs.DS 2026-08 accept novelty 7.0 of 10

    Strong coresets for ℓ_p subspace approximation of size ~O(k ε^{-2}) for 1≤p<2 and ~O(k^{p/2} ε^{-2}) for p>2, matching lower bounds up to log factors in the first regime.

  2. Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Proves that Rademacher complexity of depth-d compositional trees over finite operator vocabulary is controlled by (K b L)^{d} / sqrt(n) under Lipschitz conditions on operators.

  3. Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs

    cs.LG 2025-09 reject novelty 4.0 of 10

    The paper claims ReLU Transition Graphs of ReLU networks are expanders whose spectral gap, region entropy, and edge KL divergence bound generalization and capacity; the proofs are sketches, and the empirical checks are weak.

  4. Statistical Properties of Training & Generalization

    stat.ML 2026-06 unverdicted novelty 2.0 of 10

    Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.

Pith tools