Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 633

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

On the Convergence of Decentralized Gradient Descent

Open access
Yuan, Kun, Ling, Qing, Yin, Wotao·2016·SIAM Journal on Optimization

Abstract

Consider the consensus problem of minimizing $f(x)=\sum_{i=1}^n f_i(x)$, where $x\in{\mathbb{R}}^p$ and each $f_i$ is only known to the individual agent $i$ in a connected network of $n$ agents. To solve this problem and obtain the solution, all the agents collaborate with their neighbors through information exchange. This type of decentralized computation does not need a fusion center, offers better network load balance, and improves data privacy. This paper studies the decentralized gradient descent method [A. Nedic and A. Ozdaglar, IEEE Trans. Automat. Control, 54 (2009), pp. 48--61], in which each agent $i$ updates its local variable $x_{(i)}\in{\mathbb{R}}^n$ by combining the average of its neighbors' with a local negative-gradient step $-\alpha \nabla f_i(x_{(i)})$. The method is described by the iteration $ x_{(i)}(k+1) \gets \sum_{j=1}^n w_{ij} x_{(j)}(k) - \alpha \nabla f_i(x_{(i)}(k)),\ \text{for each agent}~i, $ where $w_{ij}$ is nonzero only if $i$ and $j$ are neighbors or $i=j$ and the matrix $W=[w_{ij}] \in \mathbb{R}^{n \times n}$ is symmetric and doubly stochastic. This paper analyzes the convergence of this iteration and derives its rate of convergence under the assumption that each $f_i$ is proper closed convex and lower bounded, $\nabla f_i$ is Lipschitz continuous with constant $L_{f_i}>0$, and the stepsize $\alpha$ is fixed. Provided that $\alpha \le \min\{(1+\lambda_n(W))/L_h,1/L_{\bar{f}}\}$, where $L_h=\max_i\{L_{f_i}\}$ and $L_{\bar{f}}=\frac{1}{n}\sum_{i=1}^{n}L_{f_i}$, the objective errors of all the local solutions and the networkwide mean solution reduce at rates of $O(1/k)$ until they reach a level of $O(\alpha)$. If $f_i$ are strongly convex with modulus $\mu_{f_i}$ and $\alpha \le \min\{(1+\lambda_n(W))/L_h,1/(L_{\bar{f}}+\mu_{\bar{f}})\}$, where $\mu_{\bar{f}}=\frac{1}{n}\sum_{i=1}^{n}\mu_{f_i}$, then all the local solutions and the mean solution converge to the global minimizer $x^*$ at a linear rate until reaching an $O(\alpha)$-neighborhood of $x^*$. We also develop an iteration for decentralized basis pursuit and establish its linear convergence to an $O(\alpha)$-neighborhood of the true sparse signal. This analysis reveals how the convergence of $ x_{(i)}(k+1) \gets \sum_{j=1}^n w_{ij} x_{(j)}(k) - \alpha \nabla f_i(x_{(i)}(k)),\ \text{for each agent}~i, $ depends on the stepsize, function convexity, and network spectrum.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1137/130943170

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 4 references

Cited by

See all 633

Metadata

Authors
Yuan, K., Ling, Q., & Yin, W.
Venue
SIAM Journal on Optimization
Published
2016-01
Volume
26
Issue
3
Pages
1835-1854
ISSN
  • 1052-6234 (ISSN-L)
  • 1095-7189
OpenAlex
W1616857247
Cited by
633
References
4
FWCI
50.53
Type
journal article
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: On the Convergence of Decentralized Gradient Descent. https://app.cochat.ai/papers/10.1137/130943170
The paper
Yuan, K., Ling, Q., & Yin, W. (2016). On the Convergence of Decentralized Gradient Descent. SIAM Journal on Optimization. https://doi.org/10.1137/130943170

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.