.png){kind=icon}
返回
Accelerated Distributed Nesterov Gradient Descent
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2019.2937496.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper considers the distributed optimization problem over a network, where the objective is to optimize a global function formed by a sum of local functions, using only local computation and communication. We develop an accelerated distributed Nesterov gradient descent method. When the objective function is convex and L-smooth, we show that it achieves a O(1/t(1.4-epsilon)) convergence rate for all epsilon is an element of (0, 1.4). We also show the convergence rate can be improved to O(1/t(2)) if the objective function is a composition of a linear map and a strongly convex and smooth function. When the objective function is mu-strongly convex and L-smooth, we show that it achieves a linear convergence rate of O([1 - C(mu/L)(5/7)](t)), where L/mu is the condition number of the objective, and C > 0 is some constant that does not depend on L/mu.
Keyword:
Convergence
Acceleration
Convex functions
Radio frequency
Linear programming
Gradient methods
Distributed algorithms
multiagent systems
optimization methods
distributed optimization
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
Observations on the Optical Deportment of the Atmosphere in Reference to the Phenomena of Putrefaction and Infection.png)
BMJOAAI
BMJIF0
OAAI分享收藏分享收藏Impaired B Cell Development and Proliferation in Absence of Phosphoinositide 3-Kinase p85αScience
ScienceIF0
PREAI
分享收藏
查看更多内容