A multi-agent projected dual gradient method with primal convergence guarantees
2013 (English)In: 51st Annual Allerton Conference on Communication, Control, and Computing, Allerton 2013, IEEE conference proceedings, 2013, 275-281 p.Conference paper (Refereed)
We consider a class of multi-agent optimization problems, where each agent is endowed with a strongly convex (but not necessarily differentiable) loss function and is subject to individual constraints composed of linear equalities, convex inequalities, and convex set constraints. We derive a novel algorithm that allows the agents to collaboratively reach a decision that minimizes the sum of the loss functions over the intersection of the individual constraints. The algorithm is based on a projected dual gradient technique and exploits the structure of the individual constraint sets to avoid costly projections. A convergence rate analysis shows that the primal iterates produced by individual agents under our algorithm converge to the primal optimal solution at a rate that is superior to alternatives in the literature. Finally, we provide a thorough comparison of our algorithm with alternatives in terms of both theoretical and algorithmic aspects.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2013. 275-281 p.
Algorithmic aspects, Constraint set, Convergence rates, Individual agent, Linear equality, Novel algorithm, Optimization problems, Primal optimal solutions, Communication, Gradient methods, Set theory, Algorithms
Other Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:kth:diva-146930DOI: 10.1109/Allerton.2013.6736535ISI: 000350802400039ScopusID: 2-s2.0-84897741610ISBN: 978-147993409-6OAI: oai:DiVA.org:kth-146930DiVA: diva2:726927
51st Annual Allerton Conference on Communication, Control, and Computing, Allerton 2013; Monticello, IL; United States; 2 October 2013 through 4 October 2013
FunderSwedish Research CouncilSwedish Foundation for Strategic Research
QC 201406192014-06-192014-06-182015-12-07Bibliographically approved