Split conformal prediction is a computationally efficient method for performing distribution-free predictive inference in regression. It involves, however, a one-time random split of the data, and the result can strongly depend on the particular split. To address this problem, we propose multi split conformal prediction, a simple method based on Markov's inequality to aggregate split conformal prediction intervals across multiple splits.

Solari, A., Djordjilovic, V. (2022). Multi split conformal prediction. STATISTICS & PROBABILITY LETTERS, 184(May 2022) [10.1016/j.spl.2022.109395].

Multi split conformal prediction

Solari A.
;
2022

Abstract

Split conformal prediction is a computationally efficient method for performing distribution-free predictive inference in regression. It involves, however, a one-time random split of the data, and the result can strongly depend on the particular split. To address this problem, we propose multi split conformal prediction, a simple method based on Markov's inequality to aggregate split conformal prediction intervals across multiple splits.
Articolo in rivista - Articolo scientifico
Conformal inference; Data splitting; Stability;
English
4-feb-2022
2022
184
May 2022
109395
none
Solari, A., Djordjilovic, V. (2022). Multi split conformal prediction. STATISTICS & PROBABILITY LETTERS, 184(May 2022) [10.1016/j.spl.2022.109395].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/354738
Citazioni
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 8
Social impact