Fast learning from α-mixing observations

H. Hang and I. Steinwart

Journal of Multivariate Analysis, 2014, vol. 127, issue C, 184-199

Abstract: We present a new oracle inequality for generic regularized empirical risk minimization algorithms learning from stationary α-mixing processes. Our main tool to derive this inequality is a rather involved version of the so-called peeling method. We then use this oracle inequality to derive learning rates for some learning methods such as empirical risk minimization (ERM), least squares support vector machines (SVMs) using given generic kernels, and SVMs using the Gaussian RBF kernels for both least squares and quantile regression. It turns out that for i.i.d. processes our learning rates for ERM and SVMs with Gaussian kernels match, up to some arbitrarily small extra term in the exponent, the optimal rates, while in the remaining cases our rates are at least close to the optimal rates.

Keywords: Alpha-mixing processes; Non-parametric classification and regression; Empirical risk minimization (ERM); Support vector machines (SVMs) (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0047259X14000426
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:jmvana:v:127:y:2014:i:c:p:184-199

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.jmva.2014.02.012

Access Statistics for this article

Journal of Multivariate Analysis is currently edited by de Leeuw, J.

More articles in Journal of Multivariate Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().