当前位置: X-MOL 学术Stoch. Process. their Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
General multilevel adaptations for stochastic approximation algorithms II: CLTs
Stochastic Processes and their Applications ( IF 1.4 ) Pub Date : 2021-02-01 , DOI: 10.1016/j.spa.2020.11.001
Steffen Dereich

Abstract In this article we establish central limit theorems for multilevel Polyak–Ruppert averaged stochastic approximation schemes. We work under very mild technical assumptions and consider the slow regime in which typical errors decay like N − δ with δ ∈ ( 0 , 1 2 ) and the critical regime in which errors decay of order N − 1 ∕ 2 log N in the runtime N of the algorithm.

中文翻译:

随机逼近算法的一般多级适应 II:CLTs

摘要 在本文中,我们建立了多级 Polyak-Ruppert 平均随机近似方案的中心极限定理。我们在非常温和的技术假设下工作,并考虑典型误差衰减如 N − δ 和 δ ∈ ( 0 , 1 2 ) 的慢速状态和运行时误差 N − 1 ∕ 2 log N 阶次衰减的临界状态N 的算法。
更新日期:2021-02-01
down
wechat
bug