Multilevel Stochastic Gradient Methods for Nested Composition Optimization

Autor: Mengdi Wang, Ethan X. Fang, Shuoguang Yang
Rok vydání: 2019
Předmět:
Zdroj: SIAM Journal on Optimization. 29:616-659
ISSN: 1095-7189
1052-6234
DOI: 10.1137/18m1164846
Popis: Stochastic gradient methods are scalable for solving large-scale optimization problems that involve empirical expectations of loss functions. Existing results mainly apply to optimization problems ...
Databáze: OpenAIRE