Mini-Batch Primal and Dual Methods for SVMs

Abstract

We address the issue of using mini-batches in stochastic optimization of SVMs. We show that the same quantity, the spectral norm of the data, controls the parallelization speedup obtained for both primal stochastic subgradient descent (SGD) and stochastic dual coordinate ascent (SCDA) methods and use it to derive novel variants of mini-batched SDCA. Our guarantees for both methods are expressed in terms of the original nonsmooth primal problem based on the hinge-loss.

View Slides

Extracted Key Phrases

3 Figures and Tables

0204020132014201520162017
Citations per Year

110 Citations

Semantic Scholar estimates that this publication has 110 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Takc2013MiniBatchPA, title={Mini-Batch Primal and Dual Methods for SVMs}, author={Martin Tak{\'a}c and Avleen Singh Bijral and Peter Richt{\'a}rik and Nathan Srebro}, booktitle={ICML}, year={2013} }