为生成模型提供可解释的置信预测集，提升高风险应用中的可信度。
Conformal Prediction for Generative Models via Adaptive Cluster-Based Density Estimation
- 基于聚类的密度估计构建预测集，降低对异常值敏感性。
- 在合成数据与气候模拟任务中，预测集体积更小、结构更简单。
- 适合需要严格且可解释不确定性估计的场景，如医疗或气候预测。
条件生成模型将输入变量映射到复杂高维分布，可在多个领域生成真实样本。然而，这类模型缺乏校准的不确定性估计，严重影响其在高风险应用中对单个输出的信任。为此，我们提出一种针对条件生成模型的系统性置信预测方法，利用模型生成样本的密度估计。引入名为CP4Gen的新方法，通过基于聚类的密度估计构建预测集，相比现有方法更少受异常值影响，更具可解释性，结构复杂度更低。在合成数据及真实世界应用（包括气候模拟任务）上的大量实验表明，CP4Gen在预测集体积和结构简单性方面表现更优。该方法为条件生成模型的不确定性估计提供了有力工具，尤其适用于需要严格且可解释预测集的场景。
原文摘要 · Abstract (English)
Conditional generative models map input variables to complex, high-dimensional distributions, enabling realistic sample generation in a diverse set of domains. A critical challenge with these models is the absence of calibrated uncertainty, which undermines trust in individual outputs for high-stakes applications. To address this issue, we propose a systematic conformal prediction approach tailored to conditional generative models, leveraging density estimation on model-generated samples. We introduce a novel method called CP4Gen, which utilizes clustering-based density estimation to construct prediction sets that are less sensitive to outliers, more interpretable, and of lower structural complexity than existing methods. Extensive experiments on synthetic datasets and real-world applications, including climate emulation tasks, demonstrate that CP4Gen consistently achieves superior performance in terms of prediction set volume and structural simplicity. Our approach offers practitioners a powerful tool for uncertainty estimation associated with conditional generative models, particularly in scenarios demanding rigorous and interpretable prediction sets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。