NIPS Proceedingsβ

Accelerated Mini-Batch Stochastic Dual Coordinate Ascent

Part of: Advances in Neural Information Processing Systems 26 (NIPS 2013)

[PDF] [BibTeX] [Reviews]


Conference Event Type: Poster


Stochastic dual coordinate ascent (SDCA) is an effective technique for solving regularized loss minimization problems in machine learning. This paper considers an extension of SDCA under the mini-batch setting that is often used in practice. Our main contribution is to introduce an accelerated mini-batch version of SDCA and prove a fast convergence rate for this method. We discuss an implementation of our method over a parallel computing system, and compare the results to both the vanilla stochastic dual coordinate ascent and to the accelerated deterministic gradient descent method of Nesterov [2007].