Distributed Mini-Batch SDCA

Martin Tak\'a\v{c}; Nathan Srebro; Peter Richt\'arik

REVIEW

Distributed Mini-Batch SDCA

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1507.08322 v1 pith:LSKCS775 submitted 2015-07-29 cs.LG math.OC

Distributed Mini-Batch SDCA

Martin Tak\'a\v{c} , Peter Richt\'arik , Nathan Srebro This is my paper

classification cs.LG math.OC

keywords analysisdatalossacrossallowsascentcombinescoordinate

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original 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).

Distributed Mini-Batch SDCA

discussion (0)