English

Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization

Machine Learning 2013-10-09 v2 Machine Learning Numerical Analysis Computation

Abstract

We introduce a proximal version of the stochastic dual coordinate ascent method and show how to accelerate the method using an inner-outer iteration procedure. We analyze the runtime of the framework and obtain rates that improve state-of-the-art results for various key machine learning optimization problems including SVM, logistic regression, ridge regression, Lasso, and multiclass SVM. Experiments validate our theoretical findings.

Keywords

Cite

@article{arxiv.1309.2375,
  title  = {Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization},
  author = {Shai Shalev-Shwartz and Tong Zhang},
  journal= {arXiv preprint arXiv:1309.2375},
  year   = {2013}
}
R2 v1 2026-06-22T01:23:52.538Z