REVIEW 3 cited by
Generalization bounds for deep convolutional 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
We prove bounds on the generalization error of convolutional networks. The bounds are in terms of the training loss, the number of parameters, the Lipschitz constant of the loss and the distance from the weights to the initial weights. They are independent of the number of pixels in the input, and the height and width of hidden feature maps. We present experiments using CIFAR-10 with varying hyperparameters of a deep convolutional network, comparing our bounds with practical generalization gaps.
Forward citations
Cited by 3 Pith papers
-
Generalization Bound for a General Class of Neural Ordinary Differential Equations
Claims a first generalization bound for nonlinear neural ODEs, but bounds the complexity of time trajectories rather than input-output maps, leaving the main theorem unproven.
-
On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing
For one-hidden-layer equivariant networks, generalization bounds depend only on filter norms and the sample size, while suitable weight sharing can match equivariance and locality adds an extra gain.
-
On the Bounds of Function Approximations
A new formalism for function approximation is used to argue that no search procedure can achieve zero error on all functions and that neural architecture search might match exhaustive search only under unstated conditions.
Discussion (0). Continue with ORCID to comment.