用于不确定性感知参数估计的对比归一化流
Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation
AI总结：
本文提出对比归一化流CNF，将数据与参数嵌入可学习映射以构造可调对比分布，结合分类器和频率学派方法，在HiggsML不确定性挑战中实现鲁棒的参数估计与不确定性量化。
摘要：
从数据中估计物理参数是机器学习（ML）在物理科学中的一项关键应用。然而，诸如探测器校准错误之类的系统不确定性会引发数据分布扭曲，从而削弱统计精度。在高能物理（HEP）和更广泛的ML场景中，在这些领域漂移下实现不确定性感知参数估计仍是一个尚未解决的问题。在本工作中，我们针对一系列对HEP至关重要的任务，应对不确定性感知参数估计的挑战。我们提出了一种基于对比归一化流（Contrastive Normalizing Flows，CNFs）的新方法，该方法在HiggsML Uncertainty Challenge数据集上取得了顶尖性能。基于二分类器可以近似模型参数似然比这一洞见，我们通过将数据和参数嵌入到一个学习得到的CNF映射中，解决了表达能力方面的实际限制以及模拟高维参数网格的高昂成本。该映射产生一个可调的对比分布，使分类在发生漂移的数据分布下仍具鲁棒性。通过结合理论分析与实证评估，我们证明：当CNF与分类器及成熟的频率学派方法相结合时，能够通过对数据分布扭曲具有鲁棒性的分类，提供有原则的参数估计和不确定性量化。
英文摘要：
Estimating physical parameters from data is a crucial application of machine learning (ML) in the physical sciences. However, systematic uncertainties, such as detector miscalibration, induce data distribution distortions that can erode statistical precision. In both high-energy physics (HEP) and broader ML contexts, achieving uncertainty-aware parameter estimation under these domain shifts remains an open problem. In this work, we address this challenge of uncertainty-aware parameter estimation for a broad set of tasks critical for HEP. We introduce a novel approach based on Contrastive Normalizing Flows (CNFs), which achieves top performance on the HiggsML Uncertainty Challenge dataset. Building on the insight that a binary classifier can approximate the model parameter likelihood ratio, we address the practical limitations of expressivity and the high cost of simulating high-dimensional parameter grids by embedding data and parameters in a learned CNF mapping. This mapping yields a tunable contrastive distribution that enables robust classification under shifted data distributions. Through a combination of theoretical analysis and empirical evaluations, we demonstrate that CNFs, when coupled with a classifier and established frequentist techniques, provide principled parameter estimation and uncertainty quantification through classification that is robust to data distribution distortions.
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。
