Fractional Order Iteration for Gradient Descent Method Based on Event-Triggered Mechanism  

作　　者：LU Jiajie WANG Yong FAN Yuan 

机构地区：[1]Department of Automation,University of Science and Technology of China,Hefei 230026,China [2]Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment,School of Electrical Engineering and Automation,Anhui University,Hefei 230601,China

出　　处：《Journal of Systems Science & Complexity》2023年第5期1927-1948,共22页系统科学与复杂性学报（英文版）

基　　金：supported by the National Natural Science Foundation of China under Grant No.61973291。

摘　　要：In this work,a novel gradient descent method based on event-triggered strategy has been proposed,which involves integer and fractional order iteration.Firstly,the convergence of integer order iterative optimization method and the stability of its associated system with integrator dynamics are linked.Based on this result,a fractional order iteration approach has been developed by modelling the system with fractional order dynamics.Secondly,to reduce the comsumption of computation,a feedback based event-triggered mechanism has been introduced to the gradient descent method.The convergence of this new event-triggered optimization algorithm is guaranteed by using a Lyapunov method,and Zeno behavior is proved to be avoided simultaneously.Lastly,the effectiveness and advantages of the proposed algorithms are verified by numerical simulations.

关 键 词：Event-triggered mechanism fractional order iteration gradient descent Zeno behavior 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]