A Generalized Lagrange Multiplier Method Support for Vector Regression Based

Cargando...
Miniatura

Fecha

2021-05

Autores

Rodríguez-Reyes, Sara E.

Título de la revista

ISSN de la revista

Título del volumen

Editor

ITESO

Resumen

Descripción

This research presents an approach to support vector regression based on the epsilon L1 and L2 formulations. In contrast to standard architectures, it explores a new formulation where the dual optimization problem results from formulating an extended Lagrangian function, introducing additional terms to include a weighted elastic net regularization structure. Additionally, the research shows the differences and similarities of this proposal with the classical support vector regression and the LASSO regression, aiming to compare them with standard models. To demonstrate the capabilities of this approach, the document includes examples of predicting some benchmark functions.

Palabras clave

Extended Lagrangian, Kernel-Based Methods, Support Vector Regression

Citación

Rodríguez-Reyes, Sara E. (2021). A Generalized Lagrange Multiplier Method Support for Vector Regression Based. Trabajo de obtención de grado, Maestría en Ciencia de Datos. Tlaquepaque, Jalisco: ITESO