arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.00838cs.LGcs.AIhep-ph
收藏

校准贝叶斯生成式机器学习以实现贝叶斯放大

Calibrating Bayesian Generative Machine Learning for Bayesiamplification

Sebastian Bieringer, Sascha Diefenbacher, Gregor Kasieczka, Mathias Trabs

AI总结:

本文提出一种校准贝叶斯生成式机器学习模型不确定性的方案,通过在连续归一化流上评估权重后验与蒙特卡洛采样的校准表现,实现用生成样本等效估计真实样本数量并展示数据放大效果。

摘要:

近年来,粒子物理学中引入了生成式与贝叶斯机器学习的结合方法,用于快速探测器模拟和推断任务。这些神经网络旨在量化由有限训练统计量引起的生成分布的不确定性。然而,分布范围不确定性的解释仍然定义不清。我们展示了一个明确的方案,用于量化贝叶斯生成式机器学习模型的校准程度。针对应用于低维玩具示例的连续归一化流,我们评估了来自平均场高斯权重后验或蒙特卡洛采样网络权重的贝叶斯不确定性的校准情况,以衡量它们在分布不稳定边缘上的行为。校准良好的不确定性随后可用于粗略估计与生成样本等效的不相关真实样本的数量,并清晰地表明分布平滑特征的数据放大效果。

英文摘要:

Recently, combinations of generative and Bayesian machine learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated distribution originating from limited training statistics. The interpretation of a distribution-wide uncertainty however remains ill-defined. We show a clear scheme for quantifying the calibration of Bayesian generative machine learning models. For a Continuous Normalizing Flow applied to a low-dimensional toy example, we evaluate the calibration of Bayesian uncertainties from either a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights, to gauge their behaviour on unsteady distribution edges. Well calibrated uncertainties can then be used to roughly estimate the number of uncorrelated truth samples that are equivalent to the generated sample and clearly indicate data amplification for smooth features of the distribution.

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。

↑