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
Signed reviews
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.
Forward citations
Cited by 4 Pith papers
-
Nearly Optimal Strong Coresets for $\ell_p$ Subspace Approximation
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.
-
Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
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.
-
Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs
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.
-
Statistical Properties of Training & Generalization
Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.
Discussion (0). Continue with ORCID to comment.