Nonlinear Acceleration of CNNs

Author name not available (Why is that?)

Publication date: 1 June 2018

Abstract: The Regularized Nonlinear Acceleration (RNA) algorithm is an acceleration method capable of improving the rate of convergence of many optimization schemes such as gradient descend, SAGA or SVRG. Until now, its analysis is limited to convex problems, but empirical observations shows that RNA may be extended to wider settings. In this paper, we investigate further the benefits of RNA when applied to neural networks, in particular for the task of image recognition on CIFAR10 and ImageNet. With very few modifications of exiting frameworks, RNA improves slightly the optimization process of CNNs, after training.

Has companion code repository: https://github.com/windows7lover/RegularizedNonlinearAcceleration

This page was built for publication: Nonlinear Acceleration of CNNs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6302417)