Distributed Mini-Batch SDCA

Martin Takáč, Peter Richtárik, Nathan Srebro

Research output: Working paper

Abstract / Description of output

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).
Original languageEnglish
PublisherArXiv
Publication statusPublished - 29 Jul 2015

Keywords / Materials (for Non-textual outputs)

  • cs.LG
  • math.OC

Fingerprint

Dive into the research topics of 'Distributed Mini-Batch SDCA'. Together they form a unique fingerprint.

Cite this