STOCHASTIC GRADIENT METHODS FOR UNCONSTRAINED OPTIMIZATION

Pesquisa Operacional

Nataša Krejić¹  Nataša Krklec Jerinkić¹ 

关键词: unconstrained optimization;    stochastic gradient;    stochastic approximation;    sample average approximation;   

DOI  :  10.1590/0101-7438.2014.034.03.0373

来源: SciELO

【 摘 要 】

This papers presents an overview of gradient based methods for minimization of noisy functions. It is assumed that the objective functions is either given with error terms of stochastic nature or given as the mathematical expectation. Such problems arise in the context of simulation based optimization. The focus of this presentation is on the gradient based Stochastic Approximation and Sample Average Approximation methods. The concept of stochastic gradient approximation of the true gradient can be successfully extended to deterministic problems. Methods of this kind are presented for the data fitting and machine learning problems.

【 授权许可】

CC BY   
 All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License