|国家预印本平台
首页|Global convergence rate analysis of unconstrained optimization methods based on probabilistic models

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

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

来源:Arxiv_logoArxiv
英文摘要

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 counterparts that use deterministic accurate models; the use of probabilistic models only increases the complexity by a constant, which depends on the probability of the models being good. We particularize and improve these results in the convex and strongly convex case. We also analyze a probabilistic cubic regularization variant that allows approximate probabilistic second-order models and show improved complexity bounds compared to probabilistic first-order methods; again, as a function of the accuracy, the probabilistic cubic regularization bounds are of the same (optimal) order as for the deterministic case.

Coralia Cartis、Katya Scheinberg

数学

Coralia Cartis,Katya Scheinberg.Global convergence rate analysis of unconstrained optimization methods based on probabilistic models[EB/OL].(2015-05-22)[2025-08-02].https://arxiv.org/abs/1505.06070.点此复制

评论