Publicação
STOCHASTIC GRADIENT METHODS FOR UNCONSTRAINED OPTIMIZATION
| 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. |
|---|---|
| Autores principais: | Krejić,Nataša |
| Outros Autores: | Jerinkić,Nataša Krklec |
| Assunto: | unconstrained optimization stochastic gradient stochastic approximation sample average approximation |
| Ano: | 2014 |
| País: | Brasil |
| Tipo de documento: | artigo |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | IBICT |
| Idioma: | inglês |
| Origem: | Oasisbr |
| 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. |
|---|
Atividades financiadas
Não foram encontrados projetos financiados.