Distributed Mini-Batch SDCA
Machine Learning
2015-07-31 v1 Optimization and Control
Abstract
We present an improved analysis of mini-batched stochastic dual coordinate ascent for regularized empirical loss minimization (i.e. SVM and SVM-type objectives). Our analysis allows for flexible sampling schemes, including where data is distribute across machines, and combines a dependence on the smoothness of the loss and/or the data spread (measured through the spectral norm).
Cite
@article{arxiv.1507.08322,
title = {Distributed Mini-Batch SDCA},
author = {Martin Takáč and Peter Richtárik and Nathan Srebro},
journal= {arXiv preprint arXiv:1507.08322},
year = {2015}
}