.png){kind=icon}
返回
Distributed Adaptive Gradient Algorithm With Gradient Tracking for Stochastic Nonconvex Optimization
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2024.3380710.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This article considers a distributed stochastic nonconvex optimization problem, where the nodes in a network cooperatively minimize a sum of $L$-smooth local cost functions with sparse gradients. By adaptively adjusting the stepsizes according to the historical (possibly sparse) gradients, a distributed adaptive gradient algorithm is proposed, in which a gradient tracking estimator is used to handle the heterogeneity between different local cost functions. We establish an upper bound on the optimality gap, which indicates that our proposed algorithm can reach a first-order stationary solution dependent on the upper bound on the variance of the stochastic gradients. Finally, numerical examples are presented to illustrate the effectiveness of the algorithm.
Keyword:
Cost function
Vectors
Upper bound
Radio frequency
Convex functions
Sparse matrices
Robots
Adaptive gradient algorithm
distributed nonconvex optimization
gradient tracking (GT)
stochastic gradient
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
.png){kind=icon}
Privacy-Preserving Dual Averaging With Arbitrary Initial Conditions for Distributed Optimization
PREAI
分享收藏分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容