In this paper we introduce a novel algorithmic framework for non-convex distributed optimization in multi-agent networks with time-varying (nonsymmetric) topology. The proposed method hinges on successive convex approximation (SCA) techniques while leveraging dynamic consensus as a mechanism to diffuse information: each agent first solves (possibly inexactly) a local convex approximation of the nonconvex original problem, and then performs local averaging operations. Asymptotic convergence to (stationary) solutions of the nonconvex problem is established. Finally, the framework is applied to a distributed nonlinear regression problem.
Distributed nonconvex optimization over time-varying networks / Di Lorenzo, P.; Scutari, G.. - (2016), pp. 4124-4128. (Intervento presentato al convegno IEEE International Conference on Acoustics, Speech, and Signal Processing tenutosi a Shanghai) [10.1109/ICASSP.2016.7472453].
Distributed nonconvex optimization over time-varying networks
Di Lorenzo P.;
2016
Abstract
In this paper we introduce a novel algorithmic framework for non-convex distributed optimization in multi-agent networks with time-varying (nonsymmetric) topology. The proposed method hinges on successive convex approximation (SCA) techniques while leveraging dynamic consensus as a mechanism to diffuse information: each agent first solves (possibly inexactly) a local convex approximation of the nonconvex original problem, and then performs local averaging operations. Asymptotic convergence to (stationary) solutions of the nonconvex problem is established. Finally, the framework is applied to a distributed nonlinear regression problem.File | Dimensione | Formato | |
---|---|---|---|
DiLorenzo_Distributed-nonconvex__2016.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
157.99 kB
Formato
Adobe PDF
|
157.99 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.