1) I show that the Gaussian process infinite trees limit of BART can be used in practice with performance close to BART itself, 2) I provide a new BART GPU implementation which is much faster than the previous state of the art.
Bayesian nonparametric regression with multivariate Normal mixtures: BART as a Gaussian process and faster BART / Giacomo Petrillo. - (2025).
Bayesian nonparametric regression with multivariate Normal mixtures: BART as a Gaussian process and faster BART
Giacomo Petrillo
2025
Abstract
1) I show that the Gaussian process infinite trees limit of BART can be used in practice with performance close to BART itself, 2) I provide a new BART GPU implementation which is much faster than the previous state of the art.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
tesi-petrillo-2025-02-23.pdf
accesso aperto
Tipologia:
Tesi di dottorato
Licenza:
Creative commons
Dimensione
4.06 MB
Formato
Adobe PDF
|
4.06 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
