ISSN:
1436-4646
Schlagwort(e):
Epi-convergence
;
epi-distance
;
stability
;
convex optimization
;
approximate solutions
;
subgradients
;
level sets
Quelle:
Springer Online Journal Archives 1860-2000
Thema:
Informatik
,
Mathematik
Notizen:
Abstract We prove that theε-optimal solutions of convex optimization problems are Lipschitz continuous with respect to data perturbations when these are measured in terms of the epi-distance. A similar property is obtained for the distance between the level sets of extended real valued functions. We also show that these properties imply that theε-subgradient mapping is Lipschitz continuous.
Materialart:
Digitale Medien
URL:
http://dx.doi.org/10.1007/BF01582147
