Size-independent sample complexity of neural networks
Noah Golowich, Alexander Rakhlin, Ohad Shamir · Information and Inference A Journal of the IMA · 2019
Abstract We study the sample complexity of learning neural networks by providing new bounds on their Rademacher complexity, assuming norm constraints on the parameter matrix of each layer. Compared to previous work, these complexity bounds have improved dependence on the network depth and, under some additional assumptions, are fully independent of the network size (both depth and width). These results are derived using some novel techniques, which may be of independent interest.