AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Electronic Research Archive Article
PDF (561.8 KB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Learning capability of the rescaled pure greedy algorithm with non-iid sampling

School of Science, Shandong Jianzhu University, Jinan 250101, China
Shandong Computer Science Center (National Supercomputer Center in Jinan), Shandong Provincial Key Laboratory of Computer Networks, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250101, China
Show Author Information

Abstract

We consider the rescaled pure greedy learning algorithm (RPGLA) with the dependent samples drawn according to a non-identical sequence of probability distributions. The generalization performance is provided by applying the independent-blocks technique and adding the drift error. We derive the satisfactory learning rate for the algorithm under the assumption that the process satisfies stationary β-mixing, and also find that the optimal rate O ( n − 1 ) can be obtained for i.i.d. processes.

Keywords

rescaled pure greedy algorithmβ-mixingnon-identical sequencesdrift errorcovering numberlearning rate

References

【1】
【1】
 
 
Crossref Google Scholar
Electronic Research Archive
Volume 31 Issue 3,
March 2023
Pages 1387-1404
DOI: 10.3934/era.2023071

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Cite this Report
Close
Close
Cite this article:
Guo Q, Cai B. Learning capability of the rescaled pure greedy algorithm with non-iid sampling. Electronic Research Archive, 2023, 31(3): 1387-1404. https://doi.org/10.3934/era.2023071

83

Views

1

Downloads

1

Crossref

1

Web of Science

0

Scopus
Received: 24 August 2022
Revised: 07 December 2022
Accepted: 14 December 2022
Published: 15 March 2023
©2023 the Author(s), licensee AIMS Press.

This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)