Computationally efficient versions of conformal predictive distributions. / Vovk, Vladimir; Petej, Ivan; Nouretdinov, Ilia; Manokhin, Valery; Gammerman, Alex.

In: Neurocomputing, Vol. 397, 15.07.2020, p. 292-308.

Research output: Contribution to journalArticle

Published

Documents

  • Accepted Manuscript

    Accepted author manuscript, 1 MB, PDF document

    Embargo ends: 2/12/20

    Licence: CC BY-NC-ND Show licence

Abstract

Conformal predictive systems are a recent modification of conformal predictors that output, in regression problems, probability distributions for labels of test observations rather than set predictions. The extra information provided by conformal predictive systems may be useful, e.g., in decision making problems. Conformal predictive systems inherit the relative computational inefficiency of conformal predictors. In this paper we discuss two computationally efficient versions of conformal predictive systems, which we call split conformal predictive systems and cross-conformal predictive systems. The main advantage of split conformal predictive systems is their guaranteed validity, whereas for cross-conformal predictive systems validity only holds empirically and in the absence of excessive randomization. The main advantage of cross-conformal predictive systems is their greater predictive efficiency.
Original languageEnglish
Pages (from-to)292-308
Number of pages17
JournalNeurocomputing
Volume397
Early online date2 Dec 2019
DOIs
Publication statusPublished - 15 Jul 2020
This open access research output is licenced under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

ID: 34814195