Acta mathematica scientia,Series B ›› 1995, Vol. 15 ›› Issue (3): 283-294.
Previous Articles Next Articles
Chen Zhong1, Fei Pusheng1, Zhou Yuncai2
Received:
Revised:
Online:
Published:
Supported by:
Abstract: According to the sequential BFGS method,in this paper we present an asynchronous parallel BFGS method in the case when the gradient information about the function is inexact.We assume that we have p+q processors, which are divided into two groups,the first group has p processors,the second group has q processors,the two groups are asynchronous parallel.If we assume the objective function is twice continuously differentiable and uniformly convex,we prove the iteration converge globally to the solution,and under some additional conditions we show the method is superlinearly convergent.Finally,we show the numerical results of this algorithm.
Key words: BFGS algorithm, superlinear convergence, parallel method
Chen Zhong, Fei Pusheng, Zhou Yuncai. ON THE CONVERGENCE OF PARALLEL BFGS METHOD[J].Acta mathematica scientia,Series B, 1995, 15(3): 283-294.
0 / / Recommend
Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks
URL: http://121.43.60.238/sxwlxbB/EN/
http://121.43.60.238/sxwlxbB/EN/Y1995/V15/I3/283
Cited