On the convergence of projected gradient processes to singular critical points |
| |
Authors: | J C Dunn |
| |
Institution: | (1) Department of Mathematics, North Carolina State University, Raleigh, North Carolina |
| |
Abstract: | The projected gradient methods treated here generate iterates by the rulex
k+1=P
(x
k
–s
k
F(x
k
)),x
1 , where is a closed convex set in a real Hilbert spaceX,s
k
is a positive real number determined by a Goldstein-Bertsekas condition,P
projectsX into ,F is a differentiable function whose minimum is sought in , and F is locally Lipschitz continuous. Asymptotic stability and convergence rate theorems are proved for singular local minimizers in the interior of , or more generally, in some open facet in . The stability theorem requires that: (i) is a proper local minimizer andF grows uniformly in near ; (ii) –F() lies in the relative interior of the coneK
of outer normals to at ; and (iii) is an isolated critical point and the defect P
(x – F(x)) –x grows uniformly within the facet containing . The convergence rate theorem imposes (i) and (ii), and also requires that: (iv)F isC
4 near and grows no slower than x–4 within the facet; and (v) the projected Hessian operatorP
F
2
F()F
is positive definite on its range in the subspaceF
orthogonal toK
. Under these conditions, {x
k
} converges to from nearby starting pointsx
1, withF(x
k
) –F() =O(k
–2) and x
k
– =O(k
–1/2). No explicit or implied local pseudoconvexity or level set compactness demands are imposed onF in this analysis. Furthermore, condition (v) and the uniform growth stipulations in (i) and (iii) are redundant in
n
. |
| |
Keywords: | Projected gradient method convex feasible sets nonconvex objective functions singular minimizers |
本文献已被 SpringerLink 等数据库收录! |
|