论文信息 - A method of feasible directions for solving nonsmooth stochastic programming problems

A method of feasible directions for solving nonsmooth stochastic programming problems

A method of feasible directions is proposed for solving stochastic programming problems with nonsmooth and nonconvex objectives. Convergence with probability 1 to stationary points is proved by means of a special Lyapunov function technique.

Andrzej Ruszczyński | A. Ruszczynski

[1] Antony R. Unwin. Progress in Nondifferentiable Optimisation , 1983 .

[2] A. Ruszczynski,et al. Stochastic approximation method with gradient averaging for unconstrained problems , 1983 .

[3] Yuri Ermoliev,et al. Stochastic Programming Methods , 1976 .

[4] Andrzej Ruszczynski,et al. Feasible direction methods for stochastic programming problems , 1980, Math. Program..

[5] R. Rockafellar. Favorable Classes of Lipschitz Continuous Functions in Subgradient Optimization , 1981 .

[6] Harold J. Kushner,et al. wchastic. approximation methods for constrained and unconstrained systems , 1978 .

[7] F. Clarke. Optimization And Nonsmooth Analysis , 1983 .