Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates

25 May 2020

Papers citing "Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates"

4 / 4 papers shown

Title
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives Aaron Defazio Francis R. Bach Simon Lacoste-Julien ODL 110 1,817 0 01 Jul 2014
A Proximal Stochastic Gradient Method with Progressive Variance Reduction Lin Xiao Tong Zhang ODL 140 738 0 19 Mar 2014
Minimizing Finite Sums with the Stochastic Average Gradient Mark Schmidt Nicolas Le Roux Francis R. Bach 257 1,246 0 10 Sep 2013
Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization Shai Shalev-Shwartz Tong Zhang 117 1,031 0 10 Sep 2012