CoChat

Distributed multi-agent optimization with state-dependent communication

Lobel, Ilan, Ozdaglar, Asuman, Feijer, Diego · 2011 · Mathematical Programming

The DOI matches its Crossref record; 33 of the 34 references it cites were found in a registry or an index.

Abstract

We study distributed algorithms for solving global optimization problems in which the objective function is the sum of local objective functions of agents and the constraint set is given by the intersection of local constraint sets of agents. We assume that each agent knows only his own local objective function and constraint set, and exchanges information with the other agents over a randomly varying network topology to update his information state. We assume a state-dependent communication model over this topology: communication is Markovian with respect to the states of the agents and the probability with which the links are available depends on the states of the agents. We study a projected multi-agent subgradient algorithm under state-dependent communication. The state-dependence of the communication introduces significant challenges and couples the study of information exchange with the analysis of subgradient steps and projection errors. We first show that the multi-agent subgradient algorithm when used with a constant stepsize may result in the agent estimates to diverge with probability one. Under some assumptions on the stepsize sequence, we provide convergence rate bounds on a “disagreement metric” between the agent estimates. Our bounds are time-nonhomogeneous in the sense that they depend on the initial starting time. Despite this, we show that agent estimates reach an almost sure consensus and converge to the same optimal solution of the global optimization problem with probability one under different assumptions on the local constraint sets and the stepsize sequence.

Overview

Integrity signals

Registry

Crossref · 10.1007/s10107-011-0467-x

Cites

33 of 33 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 33 references

Cited by

  • Distributed Optimization Over Time-Varying Directed Graphs

    Nedic, A., & Olshevsky, A. (2015) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2014.2364096 · Cited by 1,187

    “Distributed optimization of a sum of convex functions has received a surge of interest in recent years [18], [23], [9], [14], [12], [13], [28], [16], [3], [24], [5].”
  • Naïve Learning in Social Networks and the Wisdom of Crowds

    Golub, B., & Jackson, M. O. (2010) · American Economic Journal: Microeconomics · doi:10.1257/mic.2.1.112 · Cited by 979

  • Opinion Dynamics and Learning in Social Networks

    Acemoglu, D., & Ozdaglar, A. (2011) · Dynamic Games and Applications · doi:10.1007/s13235-010-0004-1 · Cited by 705

    “…the set of agents can be partitioned into groups such that each group reaches a consensus (see also [17] for a proof of convergence on Krause’s model and properties of limiting beliefs, and [66] for application of a belief-dependent communication model within a multi-agent optimization framework).”
    BackgroundSelf-citation
  • Harnessing Smoothness to Accelerate Distributed Optimization

    Qu, G., & Li, N. (2018) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2698261 · Cited by 565

    “Extensions of these work have been proposed that deal with various realistic conditions, such as stochastic subgradient errors [10], directed or random communication graphs [11]–[13], linear scaling in network size [14], and heterogeneous local constraints [15], [16].”
    Background
  • Fast Distributed Gradient Methods

    Jakovetic, D., Xavier, J., & Moura, J. M. F. (2014) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2014.2298712 · Cited by 624

    “optimization studies basically two types of algorithms with inherent tradeoffs: 1) The first type correspond to distributed gradient-like methods, namely, primal (sub) gradient [9], [10], [11], [12], [13], [14], [15], dual averaging [16], [17], [18], and primal-dual (sub)gradient [19]. These methods are attractive due…”
    Background

See all 162

Metadata

Authors
Lobel, I., Ozdaglar, A., & Feijer, D.
Affiliations
  • New York University (US)
  • Massachusetts Institute of Technology (US)
Corresponding author
Lobel, Ilan
Venue
Mathematical Programming
Published
2011-06-04
Volume
129
Issue
2
Pages
255-284
ISSN
  • 0025-5610 (ISSN-L)
  • 1436-4646
OpenAlex
W2136517470
Cited by
162
References
34
Citations by year
2024: 7 · 2023: 7 · 2022: 10 · 2021: 12 · 2020: 14 · 2019: 9 · 2018: 18 · 2017: 20 · 2016: 11 · 2015: 19 · 2014: 9 · 2013: 14 · 2012: 2
FWCI
13.41
Type
journal article
Language
en
Open access
closed
Licence
www.springer.com/tdm (tdm)
Locations
Mathematical Programming (publishedVersion)
Topics
  • Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Optimization and Variational Analysis
  • Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
Keywords
distributed optimization, multi-agent systems, random network topology, constrained global optimization, almost sure convergence, consensus, convergence rate bounds

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: Distributed multi-agent optimization with state-dependent communication. https://app.cochat.ai/papers/10.1007/s10107-011-0467-x
The paper
Lobel, I., Ozdaglar, A., & Feijer, D. (2011). Distributed multi-agent optimization with state-dependent communication. Mathematical Programming. https://doi.org/10.1007/s10107-011-0467-x

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.