Timezone: »

Large-scale probabilistic predictors with and without guarantees of validity
Vladimir Vovk · Ivan Petej · Valentina Fedorova

Tue Dec 08 04:00 PM -- 08:59 PM (PST) @ 210 C #49 #None

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.

Author Information

Vladimir Vovk (Royal Holloway, Univ of London)
Ivan Petej (Royal Holloway, University of London)
Valentina Fedorova (Yandex)