6533b85cfe1ef96bd12bd2e9
RESEARCH PRODUCT
Generalized Multitarget Linear Regression with Output Dependence Estimation
Hector GonzalezFrancesc J. FerriCarlos Morellsubject
Mathematical optimizationComputer scienceMinimization problemContext (language use)02 engineering and technologyExperimental validation01 natural sciencesRegression010104 statistics & probabilityLinear regression0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processing0101 mathematicsRegression problemsdescription
Multitarget regression has recently received attention in the context of modern, large-scale problems in which finding good enough solutions in a timely manner is crucial. Different proposed alternatives use a combination of regularizers that lead to different ways of solving the problem. In this work, we introduce a general formulation with several regularizers. This leads to a biconvex minimization problem and we use an alternating procedure with accelerated proximal gradient steps to solve it. We show that our formulation is equivalent but more efficient than some previously proposed approaches. Moreover, we introduce two new variants. The experimental validation carried out, suggests that important performance gains can be obtained with the newly proposed approach in several different publicly available multitarget regression problems.
year | journal | country | edition | language |
---|---|---|---|---|
2019-01-01 |