Large-Scale Probabilistic Predictors with and Without Guarantees of Validity
Abstract
This paper studies theoretically and empirically a method of turning machine-learning algorithms into probabilistic predictors that automatically enjoys a property of validity (perfect calibration) and is computationally efficient. The price to pay for perfect calibration is that these probabilistic predictors produce imprecise (in practice, almost precise for large data sets) probabilities. When these imprecise probabilities are merged into precise probabilities, the resulting predictors, while losing the theoretical property of perfect calibration, are consistently more accurate than the existing methods in empirical studies.
Cite
Text
Vovk et al. "Large-Scale Probabilistic Predictors with and Without Guarantees of Validity." Neural Information Processing Systems, 2015.Markdown
[Vovk et al. "Large-Scale Probabilistic Predictors with and Without Guarantees of Validity." Neural Information Processing Systems, 2015.](https://mlanthology.org/neurips/2015/vovk2015neurips-largescale/)BibTeX
@inproceedings{vovk2015neurips-largescale,
title = {{Large-Scale Probabilistic Predictors with and Without Guarantees of Validity}},
author = {Vovk, Vladimir and Petej, Ivan and Fedorova, Valentina},
booktitle = {Neural Information Processing Systems},
year = {2015},
pages = {892-900},
url = {https://mlanthology.org/neurips/2015/vovk2015neurips-largescale/}
}