Distributed kernel gradient descent algorithm for minimum error entropy principle

被引：33
|
作者：
Hu, Ting [1 ]
Wu, Qiang [2 ]
Zhou, Ding-Xuan [3 ,4 ]
机构：
[1] Wuhan Univ, Sch Math & Stat, Wuhan 430072, Peoples R China
[2] Middle Tennessee State Univ, Dept Math Sci, Murfreesboro, TN 37132 USA
[3] City Univ Hong Kong, Sch Data Sci, Kowloon, Hong Kong, Peoples R China
[4] City Univ Hong Kong, Dept Math, Kowloon, Hong Kong, Peoples R China
来源：
APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS | 2020年 / 49卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Distributed learning; Minimum error entropy; Gradient descent algorithm; Kernel method; CRITERION;
D O I：
10.1016/j.acha.2019.01.002
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
Distributed learning based on the divide and conquer approach is a powerful tool for big data processing. We introduce a distributed kernel gradient descent algorithm for the minimum error entropy principle and analyze its convergence. We show that the L-2 error decays at a minimax optimal rate under some mild conditions. As a tool we establish some concentration inequalities for U-statistics which play pivotal roles in our error analysis. Published by Elsevier Inc.
引用
收藏
页码：229 / 256
页数：28
相关论文
共 50 条
  • [21] THE MINIMUM ENTROPY PRINCIPLE IS NOT THE PRINCIPLE OF MINIMUM CROSS-ENTROPY
    CHRISTENSEN, R
    [J]. INTERNATIONAL JOURNAL OF GENERAL SYSTEMS, 1986, 12 (04) : 401 - 404
  • [22] KERNEL-BASED ONLINE GRADIENT DESCENT USING DISTRIBUTED APPROACH
    Chen, Xiaming
    [J]. MATHEMATICAL FOUNDATIONS OF COMPUTING, 2019, 2 (01): : 1 - 9
  • [23] Decision Trees Using the Minimum Entropy-of-Error Principle
    Marques de Sa, J. P.
    Gama, Joao
    Sebastiao, Raquel
    Alexandre, Luis A.
    [J]. COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS, 2009, 5702 : 799 - +
  • [24] Adaptive Filtering Based on Minimum Error Entropy Conjugate Gradient
    Li, Guoliang
    Sun, Qi
    Zhang, Ying
    Wang, Gang
    Yang, Xinyue
    Ouyang, Linqiang
    [J]. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2024, 43 (7) : 4662 - 4674
  • [25] Wavefront error correction with stochastic parallel gradient descent algorithm
    Liu Jiaguo
    Li Lin
    Hu Xinqi
    Yu Xin
    Zhao Lei
    [J]. OPTICAL DESIGN AND TESTING III, PTS 1 AND 2, 2008, 6834
  • [26] Convex Regularized Recursive Minimum Error Entropy Algorithm
    Wang, Xinyu
    Ou, Shifeng
    Gao, Ying
    [J]. ELECTRONICS, 2024, 13 (05)
  • [27] Online minimum error entropy algorithm with unbounded sampling
    Wang, Cheng
    Hu, Ting
    [J]. ANALYSIS AND APPLICATIONS, 2019, 17 (02) : 293 - 322
  • [28] Consistency analysis of an empirical minimum error entropy algorithm
    Fan, Jun
    Hu, Ting
    Wu, Qiang
    Zhou, Ding-Xuan
    [J]. APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2016, 41 (01) : 164 - 189
  • [29] Quantized Gradient-Descent Algorithm for Distributed Resource Allocation
    Zhou, Hongbing
    Yu, Weiyong
    Yi, Peng
    Hong, Yiguang
    [J]. UNMANNED SYSTEMS, 2019, 7 (02) : 119 - 136
  • [30] Fully distributed optimal dispatch of a microgrid based on consensus principle and gradient descent
    Mi Y.
    Peng J.
    Chen B.
    Wang X.
    Liu Z.
    Wang Y.
    [J]. Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control, 2022, 50 (15): : 1 - 10
12345