Automatically Adaptive Conformal Risk Control - Laboratoire Interdisciplinaire des Sciences du Numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Automatically Adaptive Conformal Risk Control

Résumé

Science and technology have a growing need for effective mechanisms that ensure reliable, controlled performance from black-box machine learning algorithms. These performance guarantees should ideally hold conditionally on the input—that is the performance guarantees should hold, at least approximately, no matter what the input. However, beyond stylized discrete groupings such as ethnicity and gender, the right notion of conditioning can be difficult to define. For example, in problems such as image segmentation, we want the uncertainty to reflect the intrinsic difficulty of the test sample, but this may be difficult to capture via a conditioning event. Building on the recent work of Gibbs et al. [2023], we propose a methodology for achieving approximate conditional control of statistical risks—the expected value of loss functions—by adapting to the difficulty of test samples. Our framework goes beyond traditional conditional risk control based on user-provided conditioning events to the algorithmic, data-driven determination of appropriate function classes for conditioning. We apply this framework to various regression and segmentation tasks, enabling finer-grained control over model performance and demonstrating that by continuously monitoring and adjusting these parameters, we can achieve superior precision compared to conventional risk-control methods.
Fichier principal
Vignette du fichier
aa-crc.pdf (8.14 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04616940 , version 1 (20-06-2024)
hal-04616940 , version 2 (21-06-2024)
hal-04616940 , version 3 (24-06-2024)

Identifiants

  • HAL Id : hal-04616940 , version 2

Citer

Vincent Blot, Anastasios N Angelopoulos, Michael I Jordan, Nicolas J-B Brunel. Automatically Adaptive Conformal Risk Control. 2024. ⟨hal-04616940v2⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More