We study the theoretical properties of a variational Bayes method in the Gaussian Process regression model. We consider the inducing variables method and derive sufficient conditions for obtaining contraction rates for the corresponding variational Bayes (VB) posterior. As examples we show that for three particular covariance kernels (Matérn, squared exponential, random series prior) the VB approach can achieve optimal, minimax contraction rates for a sufficiently large number of appropriately chosen inducing variables. The theoretical findings are demonstrated by numerical experiments.
Contraction rates for sparse variational approximations in Gaussian process regression
Szabo, Botond;
2022
Abstract
We study the theoretical properties of a variational Bayes method in the Gaussian Process regression model. We consider the inducing variables method and derive sufficient conditions for obtaining contraction rates for the corresponding variational Bayes (VB) posterior. As examples we show that for three particular covariance kernels (Matérn, squared exponential, random series prior) the VB approach can achieve optimal, minimax contraction rates for a sufficiently large number of appropriately chosen inducing variables. The theoretical findings are demonstrated by numerical experiments.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
21-1128.pdf
accesso aperto
Descrizione: article
Tipologia:
Pdf editoriale (Publisher's layout)
Licenza:
Creative commons
Dimensione
556.98 kB
Formato
Adobe PDF
|
556.98 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.