Error bound conditions and convergence of optimization methods on smooth and proximally smooth manifolds

Abstract

We analyse the convergence of the gradient projection algorithm, which is finalized with the Newton method, to a stationary point for the problem of nonconvex constrained optimization ${\min }_{x\in S}f(x)$ with a proximally smooth set $S=\{x\in R^n:g(x)=0\},g:R^n\to R^m$ and a smooth function $f$. We propose new Error bound (EB) conditions for the gradient projection method which lead to the convergence domain of the Newton method. We prove that these EB conditions are typical for a wide class of optimization problems. It is possible to reach high convergence rate of the algorithm by switching to the Newton method.