Distributed Nesterov-like gradient algorithms

In classical, centralized optimization, the Nesterov gradient algorithm reduces the number of iterations to produce an ε-accurate solution (in terms of the cost function) with respect to ordinary gradient from O(1/ε) to equation. This improvement is achieved on a class of convex functions with Lipsc...

Full description

Bibliographic Details

Published in:	2012 IEEE 51st IEEE Conference on Decision and Control (CDC) pp. 5459 - 5464
Main Authors:	Jakovetic, Dusan, Moura, J. M. F., Xavier, J.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.12.2012
Subjects:	Approximation algorithms Cloning Convergence Cost function Logistics Vectors
ISBN:	9781467320658, 146732065X
ISSN:	0191-2216
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!