caa a22 4500 386350396 CHVBK 20180307111827.0 cr unu---uuuuu 161130e198901 xx s 000 0 eng 10.1017/S0269964800000978 doi S0269964800000978 pii (NATIONALLICENCE)cambridge-10.1017/S0269964800000978 On W.P.1 Convergence of A Parallel Stochastic Approximation Algorithm [Elektronische Daten] To find zeros or locate maximum values of a regression function with noisy measurements, a commonly used algorithm is the RM or KW procedure. In various applications, the dimensionality of the problems involved might be quite large. As a result, enormous memory space and extensive computation time may be needed. Motivated by the recent progress in stochastic approximation methods for decentralized and distributed computing, a parallel stochastic approximation algorithm is developed in this paper. The essence is to take advantage of state-space decompositions, and to exploit the opportunities provided by parallel processing and asynchronous communication. In lieu of utilizing a single processor as in the classical cases, a number of parallel processors are employed to solve the underlying problem in a cooperative way. First, the large dimensional vector is partitioned into a number of subvectors with relatively small dimension, then each of the subvectors is assigned to one of the processors. The processors compute and communicate in an asynchronous manner and at random times. Under rather weak conditions, the global convergence of the parallel algorithm is obtained via the methods of randomly varying truncations. Copyright © Cambridge University Press 1989 Yin G. Department of Mathematics Wayne State University, Detroit, Michigan 48202 Zhu Y. M. Institute of Mathematical Sciences Chengdu Branch of Academia Sinica, Sichuan 610015,People's Republic of China Probability in the Engineering and Informational Sciences Cambridge University Press 3/1(1989-01), 55-75 0269-9648 3:1<55 1989 3 PES https://doi.org/10.1017/S0269964800000978 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1017/S0269964800000978 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Yin G. Department of Mathematics Wayne State University, Detroit, Michigan 48202 NATIONALLICENCE 700 1- Zhu Y. M. Institute of Mathematical Sciences Chengdu Branch of Academia Sinica, Sichuan 610015,People's Republic of China NATIONALLICENCE 773 0- Probability in the Engineering and Informational Sciences Cambridge University Press 3/1(1989-01), 55-75 0269-9648 3:1<55 1989 3 PES CC0 http://creativecommons.org/publicdomain/zero/1.0 nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-cambridge