arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.07347hep-excs.LG
收藏

洛伦兹群等变自编码器

Lorentz group equivariant autoencoders

University of California San Diego(加州大学圣地亚哥分校);Fermi National Accelerator Laboratory(费米国家加速器实验室);European Organization for Nuclear Research (CERN)(欧洲核子研究组织)

Zichun Hao, Raghav Kansal, Javier Duarte, Nadezda Chernyavskaya

AI总结:

针对高能物理机器学习模型缺乏对称性等变归纳偏置的问题,提出洛伦兹群等变自编码器LGAE,在LHC喷注任务上性能优于基线模型,还可提升异常可解释性。

摘要:

近年来,高能物理(HEP)领域在开发用于分类、模拟和异常检测等任务的机器学习(ML)模型方面开展了大量工作。这些模型通常改编自为计算机视觉或自然语言处理数据集设计的模型,缺乏适合高能物理数据的归纳偏置,例如对其固有对称性的等变性。已有研究表明,这类偏置能提升模型的性能和可解释性,并减少所需训练数据量。为此,我们开发了洛伦兹群自编码器(LGAE)——一种相对于固有正时洛伦兹群$\boldsymbol{\text{SO}}^+(3,1)$具有等变性的自编码器模型,其潜在空间存在于该群的表示中。我们介绍了其架构,并在大型强子对撞机(LHC)的喷注(jets)数据上开展了多项实验,结果表明该模型在若干压缩、重建和异常检测指标上优于图神经网络和卷积神经网络基线模型。我们还证明了这类等变模型在分析自编码器潜在空间方面的优势,可提升此类机器学习模型发现的潜在异常的可解释性。

英文摘要:

There has been significant work recently in developing machine learning (ML) models in high energy physics (HEP) for tasks such as classification, simulation, and anomaly detection. Often these models are adapted from those designed for datasets in computer vision or natural language processing, which lack inductive biases suited to HEP data, such as equivariance to its inherent symmetries. Such biases have been shown to make models more performant and interpretable, and reduce the amount of training data needed. To that end, we develop the Lorentz group autoencoder (LGAE), an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group $\mathrm{SO}^+(3,1)$, with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it outperforms graph and convolutional neural network baseline models on several compression, reconstruction, and anomaly detection metrics. We also demonstrate the advantage of such an equivariant model in analyzing the latent space of the autoencoder, which can improve the explainability of potential anomalies discovered by such ML models.

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。

↑