Oracle inequalities for convex loss functions with nonlinear targets

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Caner, M, Kock, A
Formato: Journal article
Publicado: Taylor and Francis 2015