Score-based generative modeling, informally referred to as diffusion models, continue to grow in popularity across several important domains and tasks. While they provide high-quality and diverse samples from empirical distributions, important questions remain on the reliability and trustworthiness of these sampling procedures for their responsible use in critical scenarios. Conformal prediction is a modern tool to construct finite-sample, distribution-free uncertainty guarantees for any black-box predictor. In this work, we focus on image-to-image regression tasks and we present a generalization of the Risk-Controlling Prediction Sets (RCPS) procedure, that we term $K$-RCPS, which allows to $(i)$ provide entrywise calibrated intervals for future samples of any diffusion model, and $(ii)$ control a certain notion of risk with respect to a ground truth image with minimal mean interval length. Differently from existing conformal risk control procedures, ours relies on a novel convex optimization approach that allows for multidimensional risk control while provably minimizing the mean interval length. We illustrate our approach on two real-world image denoising problems: on natural images of faces as well as on computed tomography (CT) scans of the abdomen, demonstrating state of the art performance.
Implementing Trust in Non-Small Cell Lung Cancer Diagnosis with a Conformalized Uncertainty-Aware AI Framework in Whole-Slide Images
The Hong Kong Polytechnic University(香港理工大学);Vanderbilt University Medical Center(范德堡大学医学中心);Hong Kong Baptist University(香港浸会大学);Vanderbilt University(范德堡大学)
Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling
Institut de Mathématiques de Toulouse(图卢兹数学研究所);SNCF(法国国家铁路公司);Brown University(布朗大学);Thales AVS France SAS(泰雷兹航空航天系统法国股份有限公司);IRT Saint Exupéry(圣埃克苏佩里技术研究所)
CONFIDERAI: a novel CONFormal Interpretable-by-Design score function for Explainable and Reliable Artificial Intelligence
Institute of Electronics, Information Engineering and Telecommunications - National Research Council of Italy (CNR-IEIIT)(电子信息与电信研究所 - 意大利国家科研理事会(CNR-IEIIT));Politecnico di Torino - Department of Control and Computer Engineering (DAUIN)(托尼诺理工学院 - 控制与计算机工程系(DAUIN));Rulex Innovation Labs(Rulex创新实验室)
Neural Optimal Transport Meets Multivariate Conformal Prediction
Department of ML, MBZUAI(机器学习系,MBZUAI);MBZUAI, UAE(MBZUAI,阿联酋);CMAP, École polytechnique(CMAP,巴黎高等理工学院);Ecole Polytechnique, Palaiseau, France(巴黎高等理工学院,Palaiseau,法国)
Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information
Stanford University(斯坦福大学);University of Queensland(昆士兰大学);International Computer Science Institute(国际计算机科学研究所);University of California at Berkeley(加州大学伯克利分校)