Aggregation in conformal e-classification

Vladimir Vovk

Aggregation in conformal e-classification

Vladimir Vovk

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

Abstract

Aggregating conformal predictors is a standard way of balancing their predictive and computational efficiency while retaining their validity, at least approximately. An important advantage of conformal e-predictors is that they are easier to aggregate without sacrificing their validity. This paper studies experimentally cross-conformal e-prediction, which is an existing method of aggregating conformal e-predictors, and its modifications that are conceptually simpler and more flexible.

Original language	English
Title of host publication	Proceedings of Machine Learning Research
Subtitle of host publication	2026 Conformal and Probabilistic Prediction with Applications
Editors	Johan Hallberg Szabadvary, Ulf Johansson, Henrik Bostrom, Alberto Carlevaro
Volume	329
Publication status	E-pub ahead of print - 2026

Keywords

inductive conformal e-predictors
inductive conformal predictors
cross-conformal e-predictors
cross-conformal predictors
repeated inductive conformal e-predictors
balanced inductive conformal e-predictors

Access to Document

https://arxiv.org/abs/2605.07963Licence: Other

Cite this

@inbook{5dd916db6dad4302b10abcdd8e322d9f,

title = "Aggregation in conformal e-classification",

abstract = "Aggregating conformal predictors is a standard way of balancing their predictive and computational efficiency while retaining their validity, at least approximately. An important advantage of conformal e-predictors is that they are easier to aggregate without sacrificing their validity. This paper studies experimentally cross-conformal e-prediction, which is an existing method of aggregating conformal e-predictors, and its modifications that are conceptually simpler and more flexible.",

keywords = "inductive conformal e-predictors, inductive conformal predictors, cross-conformal e-predictors, cross-conformal predictors, repeated inductive conformal e-predictors, balanced inductive conformal e-predictors",

author = "Vladimir Vovk",

year = "2026",

language = "English",

volume = "329",

editor = "\{Hallberg Szabadvary\}, Johan and Ulf Johansson and Henrik Bostrom and Alberto Carlevaro",

booktitle = "Proceedings of Machine Learning Research",

}

TY - CHAP

T1 - Aggregation in conformal e-classification

AU - Vovk, Vladimir

PY - 2026

Y1 - 2026

N2 - Aggregating conformal predictors is a standard way of balancing their predictive and computational efficiency while retaining their validity, at least approximately. An important advantage of conformal e-predictors is that they are easier to aggregate without sacrificing their validity. This paper studies experimentally cross-conformal e-prediction, which is an existing method of aggregating conformal e-predictors, and its modifications that are conceptually simpler and more flexible.

AB - Aggregating conformal predictors is a standard way of balancing their predictive and computational efficiency while retaining their validity, at least approximately. An important advantage of conformal e-predictors is that they are easier to aggregate without sacrificing their validity. This paper studies experimentally cross-conformal e-prediction, which is an existing method of aggregating conformal e-predictors, and its modifications that are conceptually simpler and more flexible.

KW - inductive conformal e-predictors

KW - inductive conformal predictors

KW - cross-conformal e-predictors

KW - cross-conformal predictors

KW - repeated inductive conformal e-predictors

KW - balanced inductive conformal e-predictors

M3 - Chapter (peer-reviewed)

VL - 329

BT - Proceedings of Machine Learning Research

A2 - Hallberg Szabadvary, Johan

A2 - Johansson, Ulf

A2 - Bostrom, Henrik

A2 - Carlevaro, Alberto

ER -