TY - JOUR
T1 - Asymptotic Agreement and Convergence of Asynchronous Stochastic Algorithms
AU - Li, Shu
AU - Başar, Tamer
N1 - Funding Information:
recommended by Associate Editor, D. A. Castanon. This work was supported in part by the Air Force Office of Scientific Research under Grant AFOSR0844il56. The authors are with the Decision and Control Laboratory. Coordinated Science Laboratory. University of Illinois, Urbana, IL 61801. IEEE Log Number 8715083.
PY - 1987/7
Y1 - 1987/7
N2 - In this paper, we present results on the convergence and asymptotic agreement of a class of asynchronous stochastic distributed algorithms which are in general time-varying, memory-dependent, and not necessarily associated with the optimization of a common cost functional. We show that convergence and agreement can be reached by distributed learning and computation under a number of conditions, in which case a separation of fast and slow parts of the algorithm is possible, leading to a separation of the estimation part from the main algorithm.
AB - In this paper, we present results on the convergence and asymptotic agreement of a class of asynchronous stochastic distributed algorithms which are in general time-varying, memory-dependent, and not necessarily associated with the optimization of a common cost functional. We show that convergence and agreement can be reached by distributed learning and computation under a number of conditions, in which case a separation of fast and slow parts of the algorithm is possible, leading to a separation of the estimation part from the main algorithm.
UR - http://www.scopus.com/inward/record.url?scp=0023383331&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0023383331&partnerID=8YFLogxK
U2 - 10.1109/TAC.1987.1104684
DO - 10.1109/TAC.1987.1104684
M3 - Article
AN - SCOPUS:0023383331
VL - 32
SP - 612
EP - 618
JO - IRE Transactions on Automatic Control
JF - IRE Transactions on Automatic Control
SN - 0018-9286
IS - 7
ER -