SDCA without Duality
Machine Learning
2015-02-24 v1
Abstract
Stochastic Dual Coordinate Ascent is a popular method for solving regularized loss minimization for the case of convex losses. In this paper we show how a variant of SDCA can be applied for non-convex losses. We prove linear convergence rate even if individual loss functions are non-convex as long as the expected loss is convex.
Keywords
Cite
@article{arxiv.1502.06177,
title = {SDCA without Duality},
author = {Shai Shalev-Shwartz},
journal= {arXiv preprint arXiv:1502.06177},
year = {2015}
}