In this letter we address nonconvex distributed consensus optimization, a popular framework for distributed big-data analytics and learning. We consider the Gradient Tracking algorithm and, by resorting to an elegant system theoretical analysis, we show that agent estimates asymptotically reach consensus to a stationary point. We take advantage of suitable coordinates to write the Gradient Tracking as the interconnection of a fast dynamics and a slow one. To use a singular perturbation analysis, we separately study two auxiliary subsystems called boundary layer and reduced systems, respectively. We provide a Lyapunov function for the boundary layer system and use Lasalle-based arguments to show that trajectories of the reduced system converge to the set of stationary points. Finally, a customized version of a Lasalle's Invariance Principle for singularly perturbed systems is proved to show the convergence properties of the Gradient Tracking.
Nonconvex Distributed Optimization via Lasalle and Singular Perturbations / Carnevale, G; Notarstefano, G. - In: IEEE CONTROL SYSTEMS LETTERS. - ISSN 2475-1456. - ELETTRONICO. - 7:(2023), pp. 9812748.301-9812748.306. [10.1109/LCSYS.2022.3187918]
Nonconvex Distributed Optimization via Lasalle and Singular Perturbations
Carnevale, G
Primo
;Notarstefano, GSecondo
2023
Abstract
In this letter we address nonconvex distributed consensus optimization, a popular framework for distributed big-data analytics and learning. We consider the Gradient Tracking algorithm and, by resorting to an elegant system theoretical analysis, we show that agent estimates asymptotically reach consensus to a stationary point. We take advantage of suitable coordinates to write the Gradient Tracking as the interconnection of a fast dynamics and a slow one. To use a singular perturbation analysis, we separately study two auxiliary subsystems called boundary layer and reduced systems, respectively. We provide a Lyapunov function for the boundary layer system and use Lasalle-based arguments to show that trajectories of the reduced system converge to the set of stationary points. Finally, a customized version of a Lasalle's Invariance Principle for singularly perturbed systems is proved to show the convergence properties of the Gradient Tracking.File | Dimensione | Formato | |
---|---|---|---|
Nonconvex_Distributed_Optimization_via_Lasalle_and_Singular_Perturbations.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale
Licenza:
Creative commons
Dimensione
459.95 kB
Formato
Adobe PDF
|
459.95 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.