A carregar...
Publicação
SLiSeS
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 3.16 MB | Adobe PDF |
Orientador(es)
Resumo(s)
The spectral gradient method is known to be a powerful low-cost tool for solving large-scale optimization problems. In this paper, our goal is to exploit its advantages in the stochastic optimization framework, especially in the case of mini-batch subsampling that is often used in big data settings. To allow the spectral coefficient to properly explore the underlying approximate Hessian spectrum, we keep the same subsample for a prefixed number of iterations before subsampling again. We analyse the required algorithmic features and the conditions for almost sure convergence, and present initial numerical results that show the advantages of the proposed method.
Descrição
Publisher Copyright: © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Palavras-chave
Finite sum minimization Line search Spectral gradient methods Subsampling Software Control and Optimization Applied Mathematics