Pith. sign in

REVIEW

Variance-Reduced Decentralized Stochastic Optimization with Gradient Tracking--Part I: GT-SAGA

Not yet reviewed by Pith; the record is open.

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 1909.11774 v3 pith:PJLEFR6N submitted 2019-09-25 math.OC

Variance-Reduced Decentralized Stochastic Optimization with Gradient Tracking--Part I: GT-SAGA

classification math.OC
keywords decentralizedcitegradientgt-sagasvrgtextbftextttalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this paper, we study decentralized empirical risk minimization problems, where the goal is to minimize a finite-sum of smooth and strongly-convex functions available over a network of nodes. In this Part I, we propose \textbf{\texttt{GT-SAGA}}, a decentralized stochastic first-order algorithm based on gradient tracking \cite{DSGT_Pu,DSGT_Xin} and a variance-reduction technique called SAGA \cite{SAGA}. We develop the convergence analysis and the iteration complexity of this algorithm. We further demonstrate various trade-offs and discuss scenarios in which \textbf{\texttt{GT-SAGA}} achieves superior performance (in terms of the number of local gradient computations required) with respect to existing decentralized schemes. In Part II \cite{GT_SVRG} of this two-part paper, we develop and analyze \textbf{\texttt{GT-SVRG}}, a decentralized gradient tracking based implementation of SVRG \cite{SVRG}, another well-known variance-reduction technique.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.