arXiv：cs.LG（机器学习，全量分类）· Carrie J. Lei-Cramer, Michael S. Jones, Laura J. Wendelberger·· 13 小时前AI 评分28
ACPNN：面向图像回归模型的自适应保形预测及其在惯性约束聚变模拟器上的应用
Adaptive Conformal Prediction for Image Regression Models with Application to an Inertial Confinement Fusion Emulator
AI 导读
研究者提出 ACPNN（Adaptive Conformal Prediction using Nearest Neighbors），一种面向图像回归的输入自适应保形预测框架，利用邻近样本信息生成局部自适应不确定性估计并保持低计算成本。其邻域结构由带 ARD 核的高斯过程学习缩放距离度量来定义。在用于模拟惯性约束聚变（ICF）的扩散模型上，ACPNN 实现了可靠且自适应的不确定性量化。
正文
Abstract:Uncertainty quantification is critical in scientific machine learning, where black-box, image-based models are increasingly deployed in high-stakes settings. In many such applications, model outputs inform costly decisions, yet most methods provide only point estimates without quantifying predictive uncertainty. This challenge is compounded by the limited accessibility and interpretability of model internals, making it difficult to assess reliability across different regions of the input space. As a result, there is a growing need for methods that can provide input-dependent uncertainty estimates to guide both model development and downstream experimentation. To address this need, we propose Adaptive Conformal Prediction using Nearest Neighbors (ACPNN), an input-adaptive conformal framework for image regression. ACPNN leverages information from neighboring samples to produce locally adaptive uncertainty estimates while maintaining low computational cost. The neighborhood structure is defined using a scaled distance metric learned via a Gaussian Process with an automatic relevance determination (ARD) kernel. We demonstrate the effectiveness of ACPNN on a diffusion model for emulating inertial confinement fusion (ICF) simulations, showing that it achieves reliable and adaptive uncertainty quantification.
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG) |
| Report number: | LLNL- LLNL-MI-2013347 |
| Cite as: | arXiv:2610.00535 [stat.ML] |
| (or arXiv:2610.00535v1 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00535 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Carrie Lei-Cramer [view email]
[v1]
Wed, 30 Sep 2026 18:19:19 UTC (1,494 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org