This article is cited in 7 papers

The method of generalized stochastic gradient for solving minimax problems with constrained variables

S. K. Zavriev, A. G. Perevozchikov

Moscow

Abstract: Minimax problems with constrained variables are considered. It is shown that under specified assumptions the internal maximum function is differentiable in the sense of Clarke and regular. The method of generalized stochastic gradient is proposed to minimize the function in the presence of constraints. It is shown how the parameters of the method can be made consistent with the convergence of a “diagonal” procedure of the Arrow-Hurewicz type in the case where the internal maximization problem is concave. .

UDC: 519.856

MSC: Primary 90C15; Secondary 90C30, 49J35, 90-08, 65K05

Received: 28.03.1989
Revised: 01.11.1989

 English version: USSR Computational Mathematics and Mathematical Physics, 1990, 30:2, 98–105

Bibliographic databases:

• 
•