Distributed Fixed Point Methods with Compressed Iterates

Adil Salim; Ahmed Khaled; Dmitry Kovalev; Martin Tak\'a\v{c}; Peter Richt\'arik; S\'elim Chraibi

REVIEW

Distributed Fixed Point Methods with Compressed Iterates

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 1912.09925 v1 pith:6DFDDL4K submitted 2019-12-20 cs.LG cs.DCcs.NAmath.NAmath.OC

Distributed Fixed Point Methods with Compressed Iterates

S\'elim Chraibi , Ahmed Khaled , Dmitry Kovalev , Peter Richt\'arik , Adil Salim , Martin Tak\'a\v{c} This is my paper

classification cs.LG cs.DCcs.NAmath.NAmath.OC

keywords compressedmethodsiteratesdistributedfirstfixedpointalgorithms

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

0 comments

read the original abstract

We propose basic and natural assumptions under which iterative optimization methods with compressed iterates can be analyzed. This problem is motivated by the practice of federated learning, where a large model stored in the cloud is compressed before it is sent to a mobile device, which then proceeds with training based on local data. We develop standard and variance reduced methods, and establish communication complexity bounds. Our algorithms are the first distributed methods with compressed iterates, and the first fixed point methods with compressed iterates.

Distributed Fixed Point Methods with Compressed Iterates

discussion (0)