Minimax Multi-Target Conformal Prediction with Applications to Imaging Inverse Problems

TMLR Paper5331 Authors

Abstract: In ill-posed imaging inverse problems, uncertainty quantification remains a fundamental challenge, especially in safety-critical applications. Recently, conformal prediction has been used to quantify the uncertainty that the inverse problem contributes to downstream tasks like image classification, image quality assessment, fat mass quantification, etc. While existing works handle only a scalar estimation target, practical applications often involve multiple targets. In response, we propose a minimax approach to multi-target conformal prediction that provides tight prediction intervals while ensuring joint marginal coverage. We then outline how our minimax approach can be applied to multi-metric blind image quality assessment, multi-task uncertainty quantification, and multi-round measurement acquisition. Finally, we numerically demonstrate the benefits of our minimax method, relative to existing multi-target conformal prediction methods, using magnetic resonance imaging (MRI) data.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Jeremias_Sulam1

Submission Number: 5331