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. |
Year | Venue | Field |
---|---|---|
2014 | CoRR | Ensembles of classifiers,AdaBoost,Computer science,Boosting (machine learning),Artificial intelligence,Rate of convergence,Deep learning,Machine learning,BrownBoost |
DocType | Volume | Citations |
Journal | abs/1411.3436 | 3 |
PageRank | References | Authors |
0.42 | 11 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shai Shalev-Shwartz | 1 | 3681 | 276.32 |