Dual Free Adaptive Minibatch SDCA for Empirical Risk Minimization

In this paper we develop an adaptive dual free Stochastic Dual Coordinate Ascent (adfSDCA) algorithm for regularized empirical risk minimization problems. This is motivated by the recent work on dual free SDCA of Shalev-Shwartz [1]. The novelty of our approach is that the coordinates to update at ea...

Full description

Bibliographic Details
Main Authors: Xi He, Rachael Tappenden, Martin Takáč
Format: Article
Language:English
Published: Frontiers Media S.A. 2018-07-01
Series:Frontiers in Applied Mathematics and Statistics
Subjects:
Online Access:https://www.frontiersin.org/article/10.3389/fams.2018.00033/full