Orateur : Ulysse Gazin
Établissement : LPSM (Paris) (France)
Dates : 2026-03-12 – 2026-03-12
Heures : 15:00 – 16:00
Lieu : IFMI 0-3
Résumé :
Titre de la conférence : Sélection de régions de prédiction conformes informativesIn supervised learning, including regression and classification, conformal methods provide prediction sets for the outcome/label with finite sample coverage for any machine learning predictor. We consider here the case where such prediction sets come after a selection process. The selection process requires that the selected prediction sets be `informative’ in a well defined sense. We consider both the classification and regression settings where the analyst may consider as informative only the sample with prediction sets small enough, excluding null values, or obeying other appropriate `monotone’ constraints. We develop a unified framework for building such informative conformal prediction sets while controlling the false coverage rate (FCR) on the selected sample. While conformal prediction sets after selection have been the focus of much recent literature in the field, the new introduced procedure, called InfoSP, is to our knowledge the first one providing FCR control for informative prediction sets.
This is a joint work with Ruth Heller, Ariane Marandon et Etienne Roquain: https://arxiv.org/abs/2403.12295