Iterative Supervised Principal Components

Juho Piironen, Aki Vehtari

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

21 Lataukset (Pure)


In high-dimensional prediction problems, where the number of features may greatly exceed the number of training instances, fully Bayesian approach with a sparsifying prior is known to produce good results but is computationally challenging. To alleviate this computational burden, we propose to use a preprocessing step where we first apply a dimension reduction to the original data to reduce the number of features to something that is computationally conveniently handled by Bayesian methods. To do this, we propose a new dimension reduction technique, called iterative supervised principal components (ISPCs), which combines variable screening and dimension reduction and can be considered as an extension to the existing technique of supervised principal components (SPCs). Our empirical evaluations confirm that, although not foolproof, the proposed approach provides very good results on several microarray benchmark datasets with very affordable computation time, and can also be very useful for visualizing high-dimensional data.
OtsikkoInternational Conference on Artificial Intelligence and Statistics, 9-11 April 2018, Playa Blanca, Lanzarote, Canary Islands
ToimittajatAmos Storkey, Fernando Perez-Cruz
TilaJulkaistu - 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Conference on Artificial Intelligence and Statistics - Playa Blanca, Espanja
Kesto: 9 huhtikuuta 201811 huhtikuuta 2018
Konferenssinumero: 21


NimiProceedings of Machine Learning Research
ISSN (elektroninen)1938-7228


ConferenceInternational Conference on Artificial Intelligence and Statistics
KaupunkiPlaya Blanca

Sormenjälki Sukella tutkimusaiheisiin 'Iterative Supervised Principal Components'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä