Decentralized Constrained Optimization: Double Averaging and Gradient Projection
Paper i proceeding, 2021

In this paper, we consider the convex, finite-sum minimization problem with explicit convex constraints over strongly connected directed graphs. The constraint is an intersection of several convex sets each being known to only one node. To solve this problem, we propose a novel decentralized projected gradient scheme based on local averaging and prove its convergence using only local functions' smoothness. Experimental studies demonstrate the effectiveness of the proposed method in both constrained and unconstrained problems.

Directed graphs

Multi-agent systems

Distributed optimization

Constrained optimization

Författare

Firooz Shahriari Mehr

Data Science och AI 1

David Bosch

Data Science och AI 1

Ashkan Panahi

Data Science och AI 1

Proceedings of the IEEE Conference on Decision and Control

07431546 (ISSN) 25762370 (eISSN)

Vol. 2021-December 2400-2406
978-1-6654-3659-5 (ISBN)

2021 60th IEEE Conference on Decision and Control (CDC)
Austin, TX, USA, ,

Effektiv datarepresentation och maskininlärning över nästa generationsnätverk

Wallenberg AI, Autonomous Systems and Software Program, 2021-01-01 -- .

Ämneskategorier

Reglerteknik

Datavetenskap (datalogi)

DOI

10.1109/CDC45484.2021.9683355

Mer information

Senast uppdaterat

2024-01-03