.png){kind=icon}
返回
Online composite optimization with time-varying regularizers
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jfranklin.2024.106884.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper investigates online composite optimization in dynamic environments, where each objective or loss function contains a time-varying nondifferentiable regularizer. To resolve it, an online proximal gradient algorithm is studied for two distinct scenarios, including convex and strongly convex objectives without the smooth condition. In both scenarios, unlike most of works, an extended version of the conventional path variation is employed to bound the considered performance metric, i.e., dynamic regret. In the convex scenario, a bound O(root T1-beta D-beta(T) + T) is obtained which is comparable to the best-known result, where D-beta(T) is the extended path variation with beta is an element of [0, 1) and T being the total number of rounds. In strongly convex case, a bound O(log T(1 + T-beta D beta(T))) on the dynamic regret is established. In the end, numerical examples are presented to support the theoretical findings.
Keyword:
Online optimization
Composite optimization
Convex optimization
Dynamic regret
Dynamic environments
期刊
J
IF:
3.7
论文数:
6.4K
被引数:
1.5W
机构
引用论文
分享收藏
Machine Learning for Predicting Field Soil Moisture Using Soil, Crop, and Nearby Weather Station Data in the Red River Valley of the North使用北部红河谷的土壤，作物和附近气象站数据预测田间土壤湿度的机器学习.png)
Soil Systems
OAAI
Soil SystemsIF0
OAAI分享收藏分享收藏
查看更多内容