Summary
We consider the problem of minimizing the sum of convex functions over a network when each component function is known (with stochastic errors) to a specific network agent. We discuss a gossip based algorithm of [2], and we analyze its error bounds for a constant stepsize that is uncoordinated across the agents.
* This work is supported by NSF Career grant 0742538.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Boyd S, Ghosh A, Prabhakar B, Shah D (2006) Randomized gossip algorithms.IEEE Trans. on Information Theory 52:2508–2530
Sundhar RS, Nedić A, Veeravalli VV (2009) Asynchronous Gossip Algorithm for stochastic optimization. Proc. of IEEE Conf. on Decision and Control
Sundhar RS, Veeravalli VV, Nedić A (2009) Distributed and non-autonomous power control through distributed convex optimization. IEEE INFOCOM
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer -Verlag Berlin Heidelberg
About this paper
Cite this paper
Ram, S.S., Nedić, A., Veeravalli, V.V. (2010). Asynchronous Gossip Algorithm for Stochastic Optimization: Constant Stepsize Analysis*. In: Diehl, M., Glineur, F., Jarlebring, E., Michiels, W. (eds) Recent Advances in Optimization and its Applications in Engineering. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12598-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-12598-0_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12597-3
Online ISBN: 978-3-642-12598-0
eBook Packages: EngineeringEngineering (R0)