Learning capability of the truncated greedy algorithm

Pure greedy algorithm （PGA）, orthogonal greedy algorithm （OGA） and relaxed greedy algorithm （RGA） are three widely used greedy type algorithms in both nonlinear approximation and supervised learning. In this paper, we apply another variant of greedy-type algorithm, called the truncated greedy algori...

Full description

Saved in:
Bibliographic Details
Published inScience China. Information sciences Vol. 59; no. 5; pp. 45 - 59
Main Authors Xu, Lin, Lin, Shaobo, Xu, Zongben
Format Journal Article
LanguageEnglish
Published Beijing Science China Press 01.05.2016
Springer Nature B.V
Subjects
Computer Science
Greedy algorithms
Information Systems and Communication Service
Research Paper
Supervised learning
TGA
启发式算法
学习能力
截断
监督学习
贪婪算法
贪心算法
非线性逼近
贪婪算法
监督学习
截断贪婪算法
supervised learning
truncated greedy algorithm
泛化能力
generalization capability
greedy algorithm
learning theory
学习理论
Online AccessGet full text

Cover

More Information
Summary:Pure greedy algorithm （PGA）, orthogonal greedy algorithm （OGA） and relaxed greedy algorithm （RGA） are three widely used greedy type algorithms in both nonlinear approximation and supervised learning. In this paper, we apply another variant of greedy-type algorithm, called the truncated greedy algorithm （TGA） in the realm of supervised learning and study its learning performance. We rigorously prove that TGA is better than PGA in the sense that TGA possesses the faster learning rate than PGA. Furthermore, in some special cases, we also prove that TGA outperforms OGA and RGA. All these theoretical assertions are verified by both toy simulations and real data experiments.
Bibliography:11-5847/TP
Pure greedy algorithm （PGA）, orthogonal greedy algorithm （OGA） and relaxed greedy algorithm （RGA） are three widely used greedy type algorithms in both nonlinear approximation and supervised learning. In this paper, we apply another variant of greedy-type algorithm, called the truncated greedy algorithm （TGA） in the realm of supervised learning and study its learning performance. We rigorously prove that TGA is better than PGA in the sense that TGA possesses the faster learning rate than PGA. Furthermore, in some special cases, we also prove that TGA outperforms OGA and RGA. All these theoretical assertions are verified by both toy simulations and real data experiments.
supervised learning, learning theory, generalization capability, greedy algorithm, truncated greedy algorithm
ISSN:1674-733X
1869-1919
DOI:10.1007/s11432-016-5536-6