RT journal article
T1 A cost-sensitive constrained Lasso
A1 Blanquero, Rafael
A1 Carrizosa, Emilio
A1 Ramírez Cobo, Josefa
A1 Sillero-Denamiel, M. Remedios
A2 Estadística e Investigación Operativa
K1 Performance Constraints
K1 Cost-Sensitive Learning
K1 Sparse Solutions
K1 Sample Average Approximation
K1 Heterogeneity
K1 Lasso
AB The Lasso has become a benchmark data analysis procedure, and numerous variants have been proposed in the literature. Although the Lasso formulations are stated so that overall prediction error is optimized, no full control over the accuracy prediction on certain individ- uals of interest is allowed.In this work we propose a novel version of the Lasso in which quadratic performance con- straints are added to Lasso-based objective functions, in such a way that threshold values are set to bound the prediction errors in the different groups of interest (not necessarily disjoint). As a result, a constrained sparse regression model is defined by a nonlinear optimization prob- lem. This cost-sensitive constrained Lasso has a direct application in heterogeneous samples where data are collected from distinct sources, as it is standard in many biomedical contexts. Both theoretical properties and empirical studies concerning the new method are explored in this paper. In addition, two illustrations of the method on biomedical and sociological contexts are considered.
PB Springer
SN 18625347
YR 2021
FD 2021
LK http://hdl.handle.net/10498/30592
UL http://hdl.handle.net/10498/30592
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 07-nov-2026