Barron Approximation and locally optimal weight densities for shallow neural networks
Organizations: School of Mathematical and Statistical Sciences, University of Texas Rio Grande Valley, Brownsville, TX 78520, USA
Abstract
Mean field theories provide optimization results for shallow neural networks by analyzing the weight distribution in infinite width limits. Corresponding results for finite sized networks are obtained by particle approximations, for which sharp quantitative bounds are still an open problem. In this paper, we consider a modified mean field loss, which allows a more fine grained control over finite sized networks. We prove convexity and equidistribution properties, which directly lead to Barron type approximation results for networks sampled from local loss minimizers. We demonstrate that particle approximations of the new loss function naturally lead to gradient descent methods with dropout type regularization.
Figures & tables
Shallow Neural Networks
Shallow neural networks use one or a few layers to learn functions, offering a setting to study efficient approximation, training dynamics, and limits of depth.
See all 64 papers