A Fast Distributed Asynchronous Newton-Based Optimization Algorithm

One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a networked system. Most of the existing work in this area focuses on developing distributed algorithms in a synchronous setting under the presence...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on automatic control Ročník 65; číslo 7; s. 2769 - 2784
Hlavní autoři: Mansoori, Fatemeh, Wei, Ermin
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.07.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Agents and autonomous systems
Algorithms
Approximation algorithms
asynchronous algorithms
Clocks
Convergence
Delays
Linear programming
network analysis and control
Optimization
optimization algorithms
Symmetric matrices
Synchronism
ISSN:0018-9286, 1558-2523
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a networked system. Most of the existing work in this area focuses on developing distributed algorithms in a synchronous setting under the presence of a central clock, where the agents need to wait for the slowest one to finish the update, before proceeding to the next iterate. Asynchronous distributed algorithms remove the need for a central coordinator, reduce the synchronization wait, and allow some agents to compute faster and execute more iterations. In the asynchronous setting, the only known algorithms for solving this problem could achieve an either linear or sublinear rate of convergence. In this paper, we build upon the existing literature to develop and analyze an asynchronous Newton-based method to solve a penalized version of the problem. We show that this algorithm guarantees almost sure convergence with a global linear and local quadratic rate in expectation. Numerical studies confirm the superior performance of our algorithm against other asynchronous methods.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9286
1558-2523
DOI:10.1109/TAC.2019.2933607