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...
| Главные авторы: | , |
|---|---|
| Формат: | Journal article |
| Опубликовано: |
Springer Berlin Heidelberg
2017
|