SelfieBoost: A Boosting Algorithm for Deep Learning
Shai Shalev‐Shwartz · arXiv (Cornell University) · 2014
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 $\log(1/ε)$ convergence rate for SelfieBoost under some "SGD success" assumption which seems to hold in practice.