arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.03791stat.MLcs.CVcs.LG
收藏

如何信任你的扩散模型:一种用于共形风险控制的凸优化方法

How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control

Johns Hopkins University(约翰斯·霍普金斯大学)

Jacopo Teneggi, Matthew Tivnan, J. Webster Stayman, Jeremias Sulam

AI总结:

本文提出K-RCPS,一种基于凸优化的共形风险控制方法,用于为扩散模型在图像回归任务中提供逐元素校准区间并控制风险,在图像去噪上达到最先进性能。

摘要:

基于分数的生成建模(非正式地称为扩散模型)在多个重要领域和任务中持续受到欢迎。尽管它们能从经验分布中生成高质量且多样化的样本,但在关键场景中负责任地使用这些采样过程的可靠性和可信度方面仍存在重要问题。共形预测是一种现代工具,可为任何黑盒预测器构建有限样本、无分布假设的不确定性保证。在这项工作中,我们聚焦于图像到图像的回归任务,并提出了一种称为$K$-RCPS的风险控制预测集(RCPS)过程的推广,它能够(i)为任何扩散模型的未来样本提供逐元素校准的区间,以及(ii)在最小平均区间长度的前提下,控制相对于地面真实图像的某种风险概念。与现有的共形风险控制程序不同,我们的方法依赖于一种新颖的凸优化方法,该方法允许在多维风险控制的同时,可证明地最小化平均区间长度。我们在两个真实世界的图像去噪问题上展示了我们的方法:在自然人脸图像以及腹部计算机断层扫描(CT)图像上,展示了最先进的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑