Low-rank layers in deep networks yield Gaussian complexity bounds where the rank factor appears once, not once per layer, improving on prior norm-based bounds.
A Chain Rule for the Expected Suprema of Bernoulli Processes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We obtain an upper bound on the expected supremum of a Bernoulli process indexed by the image of an index set under a uniformly Lipschitz function class in terms of properties of the index set and the function class, extending an earlier result of Maurer for Gaussian processes. The proof makes essential use of recent results of Bednorz and Latala on the boundedness of Bernoulli processes.
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On Generalization Bounds for Neural Networks with Low Rank Layers
Low-rank layers in deep networks yield Gaussian complexity bounds where the rank factor appears once, not once per layer, improving on prior norm-based bounds.