Stručni rad

LASSO Regression

Nikola Kraljević ; student, Fakultet elektrotehnike i računarstva u Zagrebu, Sveučilište u Zagrebu
Igor Velčić orcid.org/0000-0003-2494-2230 ; Zavod za primijenjenu matematiku, Fakultet elektrotehnike i računarstva u Zagrebu, Sveučilište u Zagrebu *

* Dopisni autor.

Sažetak

This paper gives a comparison between the Ridge and Lasso regression methods. We also explain the coordinate descent algorithm used for the estimation of the parameters in Lasso regression. The properties of both models are demonstrated on simulated data, as well as the application of the Bootstrap method for the Lasso model.

Ključne riječi

linear regression, lasso regression, ridge regression, sparse data

Hrčak ID:

340961

URI

https://hrcak.srce.hr/340961

Datum izdavanja:

10.12.2025.

Podaci na drugim jezicima: hrvatski

Posjeta: 498 *