Pith. sign in

REVIEW 2 cited by

A Stochastic Proximal Gradient Framework for Decentralized Non-Convex Composite Optimization: Topology-Independent Sample Complexity and Communication Efficiency

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 2110.01594 v1 pith:SWOXMUY7 submitted 2021-10-04 math.OC

A Stochastic Proximal Gradient Framework for Decentralized Non-Convex Composite Optimization: Topology-Independent Sample Complexity and Communication Efficiency

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

Decentralized optimization is a promising parallel computation paradigm for large-scale data analytics and machine learning problems defined over a network of nodes. This paper is concerned with decentralized non-convex composite problems with population or empirical risk. In particular, the networked nodes are tasked to find an approximate stationary point of the average of local, smooth, possibly non-convex risk functions plus a possibly non-differentiable extended valued convex regularizer. Under this general formulation, we propose the first provably efficient, stochastic proximal gradient framework, called ProxGT. Specifically, we construct and analyze several instances of ProxGT that are tailored respectively for different problem classes of interest. Remarkably, we show that the sample complexities of these instances are network topology-independent and achieve linear speedups compared to that of the corresponding centralized optimal methods implemented on a single node.

discussion (0)

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

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Distributed Normal Map-based Stochastic Proximal Gradient Methods over Networks

    math.OC 2024-12 unverdicted novelty 6.0

    norM-DSGT and norM-ED achieve centralized stochastic proximal-gradient rates for distributed composite objectives, with norM-ED transient time O(n^3/(1-λ)^2).

  2. Stochastic versus Deterministic in Stochastic Gradient Descent

    math.OC 2025-09 unverdicted novelty 5.0

    Treating stochastic and deterministic gradients separately in mini-batch SGD yields faster convergence and smaller error radius than uniform treatment, with further gains under strong convexity.