New algorithms for the numerical solution of optimization problems involving the l0 pseudo-norm are proposed. They are designed to use a recently proposed computational methodology that is able to deal numerically with finite, infinite and infinitesimal numbers. This new methodology introduces an infinite unit of measure expressed by the numeral ⃝1 (grossone) and indicating the number of elements of the set IN, of natural numbers. We show how the numerical system built upon ⃝1 and the proposed approximation of the l0 pseudo-norm in terms of ⃝1 can be successfully used in the solution of elastic net regularization problems and sparse support vector machines classification problems.
The use of grossone in elastic net regularization and sparse support vector machines
De Leone, Renato
;Egidi, Nadaniela;Fatone, Lorella
2020-01-01
Abstract
New algorithms for the numerical solution of optimization problems involving the l0 pseudo-norm are proposed. They are designed to use a recently proposed computational methodology that is able to deal numerically with finite, infinite and infinitesimal numbers. This new methodology introduces an infinite unit of measure expressed by the numeral ⃝1 (grossone) and indicating the number of elements of the set IN, of natural numbers. We show how the numerical system built upon ⃝1 and the proposed approximation of the l0 pseudo-norm in terms of ⃝1 can be successfully used in the solution of elastic net regularization problems and sparse support vector machines classification problems.File | Dimensione | Formato | |
---|---|---|---|
paperSoftComp.pdf
accesso aperto
Tipologia:
Documento in Pre-print
Licenza:
DRM non definito
Dimensione
325.73 kB
Formato
Adobe PDF
|
325.73 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.