SelfieBoost: A Boosting Algorithm for Deep Learning
classification
📊 stat.ML
cs.LG
keywords
selfieboostboostingalgorithmdeeplearningaccuracyadaboostalgorithms
read the original 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 $\log(1/\epsilon)$ convergence rate for SelfieBoost under some "SGD success" assumption which seems to hold in practice.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.