TY - GEN
T1 - A stochastic primal-dual algorithm for distributed asynchronous composite optimization
AU - Bianchi, Pascal
AU - Hachem, Walid
AU - Iutzeler, Franck
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/2/5
Y1 - 2014/2/5
N2 - Consider a network where each agent has a private composite function (e.g. the sum of a smooth and a non-smooth function). The problem we address here is to And a minimize! of the aggregate cost (the sum of the agents functions) in a distributed manner. In this paper, we combine recent results on primal-dual optimization and coordinate descent to propose an asynchronous distributed algorithm for composite optimization.
AB - Consider a network where each agent has a private composite function (e.g. the sum of a smooth and a non-smooth function). The problem we address here is to And a minimize! of the aggregate cost (the sum of the agents functions) in a distributed manner. In this paper, we combine recent results on primal-dual optimization and coordinate descent to propose an asynchronous distributed algorithm for composite optimization.
KW - Consensus algorithms
KW - Coordinate descent
KW - Distributed optimization
KW - Primal-dual algorithm
UR - https://www.scopus.com/pages/publications/84949927850
U2 - 10.1109/GlobalSIP.2014.7032215
DO - 10.1109/GlobalSIP.2014.7032215
M3 - Conference contribution
AN - SCOPUS:84949927850
T3 - 2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
SP - 732
EP - 736
BT - 2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2014
Y2 - 3 December 2014 through 5 December 2014
ER -