Error analysis for coefficient-based regularized regression in additive models

Yanfang Tao, Biqin Song and Luoqing Li

Statistics & Probability Letters, 2018, vol. 134, issue C, 22-28

Abstract: This paper considers a coefficient-based additive model with the ℓq-regularizer (1≤q≤2). Error bounds are established for the proposed model by integrating the stepping stone technique and the concentration estimate with empirical covering numbers. From error analysis, we obtain a sharp learning rate that can be arbitrarily close to O(nϵ−1) under mild conditions.

Keywords: Additive models; Coefficient-based regularization; Generalization bound (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167715217303152
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:stapro:v:134:y:2018:i:c:p:22-28

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

DOI: 10.1016/j.spl.2017.10.001

Access Statistics for this article

Statistics & Probability Letters is currently edited by Somnath Datta and Hira L. Koul

More articles in Statistics & Probability Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().