@inproceedings{Kern:2016,
author = {Kern, T and Gyorgy, A},
publisher = {Neural Information Processing Systems Foundation, Inc.},
title = {SVRG++ with non-uniform sampling},
url = {http://hdl.handle.net/10044/1/45978},
year = {2016}
}

Download

TY  - CPAPER
AB  - SVRG++ is a recent randomized optimization algorithm designed to solve non-strongly convex smooth composite optimization problems in the large data regime.In this paper we combine SVRG++ with non-uniform sampling of the data points(already present in the original SVRG algorithm), leading to an algorithm with thebest sample complexity to date and state-of-the art empirical performance. Whilethe combination and the analysis of the algorithm is admittedly straightforward,our experimental results show significant improvement over the original SVRG++method with the new method outperforming all competitors on datasets where thesmoothness of the components varies. This demonstrates that, despite its simplicityand limited novelty, this extension is important in practice.
AU  - Kern,T
AU  - Gyorgy,A
PB  - Neural Information Processing Systems Foundation, Inc.
PY  - 2016///
TI  - SVRG++ with non-uniform sampling
UR  - http://hdl.handle.net/10044/1/45978
ER  - 

Download