Loading...
conference paper
Adaptive stochastic convex optimization over networks
2013
Proceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton)
In this work, we study the task of distributed optimization over a network of learners in which each learner possesses a convex cost function, a set of affine equality constraints, and a set of convex inequality constraints. We propose a distributed diffusion algorithm based on penalty methods that allows the network to cooperatively optimize a global cost function, subject to all constraints and without using projection steps. We show that when sufficiently small step-sizes are employed, the expected distance between the optimal solution vector and that obtained at each node in the network can be made arbitrarily small.
Type
conference paper
Authors
Publication date
2013
Publisher
Published in
Proceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton)
Start page
1272
End page
1277
Peer reviewed
REVIEWED
EPFL units
Event name | Event place | Event date |
Monticello, IL | October 2-4, 2013 | |
Available on Infoscience
December 19, 2017
Use this identifier to reference this record