Inductive Venn-Abers Predictive Distribution. / Nouretdinov, Ilia; Volkhonskiy, Denis; Lim, Pitt; Toccaceli, Paolo; Gammerman, Alexander.

7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018). Vol. 91 2018. p. 15-36 (Proceedings of Machine Learning Research).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Standard

Inductive Venn-Abers Predictive Distribution. / Nouretdinov, Ilia; Volkhonskiy, Denis; Lim, Pitt; Toccaceli, Paolo; Gammerman, Alexander.

7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018). Vol. 91 2018. p. 15-36 (Proceedings of Machine Learning Research).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Nouretdinov, I, Volkhonskiy, D, Lim, P, Toccaceli, P & Gammerman, A 2018, Inductive Venn-Abers Predictive Distribution. in 7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018). vol. 91, Proceedings of Machine Learning Research, pp. 15-36, The 7th Symposium on Conformal and Probabilistic Prediction with Applications, Maastricht, Netherlands, 11/06/18.

APA

Nouretdinov, I., Volkhonskiy, D., Lim, P., Toccaceli, P., & Gammerman, A. (2018). Inductive Venn-Abers Predictive Distribution. In 7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018) (Vol. 91, pp. 15-36). (Proceedings of Machine Learning Research).

Vancouver

Nouretdinov I, Volkhonskiy D, Lim P, Toccaceli P, Gammerman A. Inductive Venn-Abers Predictive Distribution. In 7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018). Vol. 91. 2018. p. 15-36. (Proceedings of Machine Learning Research).

Author

Nouretdinov, Ilia ; Volkhonskiy, Denis ; Lim, Pitt ; Toccaceli, Paolo ; Gammerman, Alexander. / Inductive Venn-Abers Predictive Distribution. 7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018). Vol. 91 2018. pp. 15-36 (Proceedings of Machine Learning Research).

BibTeX

@inproceedings{8425bb1dc79f4b4fa0159f37dacd2815,
title = "Inductive Venn-Abers Predictive Distribution",
abstract = "Venn predictors are a distribution-free probabilistic prediction framework that transforms the output of a scoring classifier into a (multi-)probabilistic prediction that has calibration guarantees, with the only requirement of an i.i.d. assumption for calibration and test data.In this paper, we extend the framework from classification (where probabilities are predicted for a discrete number of labels) to regression (where labels form a continuum). We show how Venn Predictors can be applied on top of any regression method to obtain calibrated predictive distributions, without requiring assumptions beyond i.i.d. of calibration and test sets. This is contrasted with methods such as Bayesian Linear Regression, for which the calibration guarantee instead relies on specific probabilistic assumptions on the distribution of the data.The adaptation of Venn Machine to regression required a theoretical analysis of the transductive and inductive forms of the predictor. We identify potential consistency problems and provide solutions for them.Finally, to illustrate their advantages, we apply regression Venn Predictors to the medical problem of predicting the survival time after Percutaneous Coronary Intervention, a potentially risky procedure that improves blood flow to a patient’s heart. The predictive distributions obtained with this method allow a variety of interpretations that include probability of survival time exceeding a chosen threshold or the shortest survival time guaranteed with a given probability.",
keywords = "reliable prediction, Venn machine, regression",
author = "Ilia Nouretdinov and Denis Volkhonskiy and Pitt Lim and Paolo Toccaceli and Alexander Gammerman",
year = "2018",
month = "6",
language = "English",
volume = "91",
series = "Proceedings of Machine Learning Research",
pages = "15--36",
booktitle = "7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018)",

}

RIS

TY - GEN

T1 - Inductive Venn-Abers Predictive Distribution

AU - Nouretdinov, Ilia

AU - Volkhonskiy, Denis

AU - Lim, Pitt

AU - Toccaceli, Paolo

AU - Gammerman, Alexander

PY - 2018/6

Y1 - 2018/6

N2 - Venn predictors are a distribution-free probabilistic prediction framework that transforms the output of a scoring classifier into a (multi-)probabilistic prediction that has calibration guarantees, with the only requirement of an i.i.d. assumption for calibration and test data.In this paper, we extend the framework from classification (where probabilities are predicted for a discrete number of labels) to regression (where labels form a continuum). We show how Venn Predictors can be applied on top of any regression method to obtain calibrated predictive distributions, without requiring assumptions beyond i.i.d. of calibration and test sets. This is contrasted with methods such as Bayesian Linear Regression, for which the calibration guarantee instead relies on specific probabilistic assumptions on the distribution of the data.The adaptation of Venn Machine to regression required a theoretical analysis of the transductive and inductive forms of the predictor. We identify potential consistency problems and provide solutions for them.Finally, to illustrate their advantages, we apply regression Venn Predictors to the medical problem of predicting the survival time after Percutaneous Coronary Intervention, a potentially risky procedure that improves blood flow to a patient’s heart. The predictive distributions obtained with this method allow a variety of interpretations that include probability of survival time exceeding a chosen threshold or the shortest survival time guaranteed with a given probability.

AB - Venn predictors are a distribution-free probabilistic prediction framework that transforms the output of a scoring classifier into a (multi-)probabilistic prediction that has calibration guarantees, with the only requirement of an i.i.d. assumption for calibration and test data.In this paper, we extend the framework from classification (where probabilities are predicted for a discrete number of labels) to regression (where labels form a continuum). We show how Venn Predictors can be applied on top of any regression method to obtain calibrated predictive distributions, without requiring assumptions beyond i.i.d. of calibration and test sets. This is contrasted with methods such as Bayesian Linear Regression, for which the calibration guarantee instead relies on specific probabilistic assumptions on the distribution of the data.The adaptation of Venn Machine to regression required a theoretical analysis of the transductive and inductive forms of the predictor. We identify potential consistency problems and provide solutions for them.Finally, to illustrate their advantages, we apply regression Venn Predictors to the medical problem of predicting the survival time after Percutaneous Coronary Intervention, a potentially risky procedure that improves blood flow to a patient’s heart. The predictive distributions obtained with this method allow a variety of interpretations that include probability of survival time exceeding a chosen threshold or the shortest survival time guaranteed with a given probability.

KW - reliable prediction

KW - Venn machine

KW - regression

M3 - Conference contribution

VL - 91

T3 - Proceedings of Machine Learning Research

SP - 15

EP - 36

BT - 7th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2018)

ER -