Oracle Inequalities for Convex Loss Functions with Nonlinear Targets

Mehmet Caner and Anders Kock

Econometric Reviews, 2016, vol. 35, issue 8-10, 1377-1411

Abstract: This article considers penalized empirical loss minimization of convex loss functions with unknown target functions. Using the elastic net penalty, of which the Least Absolute Shrinkage and Selection Operator (Lasso) is a special case, we establish a finite sample oracle inequality which bounds the loss of our estimator from above with high probability. If the unknown target is linear, this inequality also provides an upper bound of the estimation error of the estimated parameter vector. Next, we use the non-asymptotic results to show that the excess loss of our estimator is asymptotically of the same order as that of the oracle. If the target is linear, we give sufficient conditions for consistency of the estimated parameter vector. We briefly discuss how a thresholded version of our estimator can be used to perform consistent variable selection. We give two examples of loss functions covered by our framework.

Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://hdl.handle.net/10.1080/07474938.2015.1092797 (text/html)
Access to full text is restricted to subscribers.

Related works:
Working Paper: Oracle Inequalities for Convex Loss Functions with Non-Linear Targets (2013)
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:taf:emetrv:v:35:y:2016:i:8-10:p:1377-1411

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/LECR20

DOI: 10.1080/07474938.2015.1092797

Access Statistics for this article

Econometric Reviews is currently edited by Dr. Essie Maasoumi

More articles in Econometric Reviews from Taylor & Francis Journals
Bibliographic data for series maintained by ().