Smoothed functionals and constrained stochastic approximation
暂无分享,去创建一个
The problem of finding an extremum for a nonconvex function under convex constraints is considered. The original nonconvex function is replaced by an auxiliary one, called a smoothed function, which possesses some nice properties. Operating with the smoothed function and the given convex constraints the global extremum of the original problem is found.
[1] M. T. Wasan. Stochastic Approximation , 1969 .