Decentralized AdaBoost algorithm over sensor networks

In this paper, we study the decentralized AdaBoost problem over sensor networks, and propose a fully decentralized AdaBoost algorithm, where each sensor can obtain the centralized global solution without transmission of private dataset. By decomposing the centralized cost function into a summation o...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neurocomputing (Amsterdam) Ročník 479; s. 37 - 46
Hlavní autoři: An, Xibin, Hu, Chen, Li, Zhenhua, Lin, Haoshen, Liu, Gang
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 28.03.2022
Témata:
Classification
Decentralized AdaBoost
Distributed optimization
Sensor networks
Sensor networks
Distributed optimization
Decentralized AdaBoost
Classification
ISSN:0925-2312, 1872-8286
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we study the decentralized AdaBoost problem over sensor networks, and propose a fully decentralized AdaBoost algorithm, where each sensor can obtain the centralized global solution without transmission of private dataset. By decomposing the centralized cost function into a summation of local ones, we convert decentralized AdaBoost problem into a distributed optimization problem, and design a distributed alternating minimization method to solve it. In order to improve convergence rate, motivated by Nesterov gradient descent method, we propose a fast decentralized AdaBoost algorithm. Then, we prove the convergence of proposed algorithms. Moreover, we deduce decentralized AdaBoost algorithm for logistic regression in detail. The simulations with Spam-Email dataset illustrate the effectiveness of proposed algorithms.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2022.01.015