SelfieBoost: A Boosting Algorithm for Deep Learning

Abstract

We describe and analyze a new boosting algorithm for deep learning called SelfieBoost. Unlike other boosting algorithms, like AdaBoost, which construct ensembles of classifiers, SelfieBoost boosts the accuracy of a single network. We prove a (1/) convergence rate for SelfieBoost under some "SGD success" assumption which seems to hold in practice.

Tasks

Reproductions