How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control
- 1. Johns Hopkins University
Description
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.
Files
checkpoints.zip
Files
(6.6 GB)
Name | Size | Download all |
---|---|---|
md5:7541ea6583c1a5eacf80e149132f482b
|
3.6 GB | Preview Download |
md5:9e06ca04ef4c788ffea9efe8efdf9dc5
|
3.0 GB | Preview Download |