Global convergence rate analysis of unconstrained optimization methods based on probabilistic models

We present global convergence rates for a line-search method which is based on random first-order models and directions whose quality is ensured only with certain probability. We show that in terms of the order of the accuracy, the evaluation complexity of such a method is the same as its counterpar...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron: Cartis, C, Scheinberg, K
Fformat: Journal article
Cyhoeddwyd: Springer Berlin Heidelberg 2017

Eitemau Tebyg