Noise-Adaptive Conformal Classification with Marginal Coverage
Journal:
arXiv
Published Date:
Jan 29, 2025
Abstract
Conformal inference provides a rigorous statistical framework for uncertainty
quantification in machine learning, enabling well-calibrated prediction sets
with precise coverage guarantees for any classification model. However, its
reliance on the idealized assumption of perfect data exchangeability limits its
effectiveness in the presence of real-world complications, such as low-quality
labels -- a widespread issue in modern large-scale data sets. This work tackles
this open problem by introducing an adaptive conformal inference method capable
of efficiently handling deviations from exchangeability caused by random label
noise, leading to informative prediction sets with tight marginal coverage
guarantees even in those challenging scenarios. We validate our method through
extensive numerical experiments demonstrating its effectiveness on synthetic
and real data sets, including CIFAR-10H and BigEarthNet.
