STOCHASTIC GRADIENT METHODS FOR UNCONSTRAINED OPTIMIZATION

AUTOR(ES)

Krejić, Nataša, Jerinkić, Nataša Krklec

FONTE

Pesqui. Oper.

DATA DE PUBLICAÇÃO

2014-12

RESUMO

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.

Documentos Relacionados

• Step-size estimation for unconstrained optimization methods
• Estudo de alguns metodos determinsticos de otimização irrestrita
• Comparing stochastic optimization methods to solve the medium-term operation planning problem
• PERFORMANCE COMPARISON OF SCENARIO-GENERATION METHODS APPLIED TO A STOCHASTIC OPTIMIZATION ASSET-LIABILITY MANAGEMENT MODEL
• Optimization of biplanar gradient coils for magnetic resonance imaging