对称性、安全性与自监督
Symmetries, Safety, and Self-Supervision
AI总结:
本文提出 JetCLR,利用自监督对比学习和置换不变 transformer-encoder,将喷注低层数据映射为保留物理对称性与判别信息的新物理无关表示。
摘要:
对撞机搜索面临的挑战是,如何定义一种高维数据表示,使物理对称性得到显式体现、判别特征得以保留,并且表示的选择不依赖于新物理假设。我们引入 JetCLR,通过自监督对比学习来解决从低层数据到优化可观测量的映射问题。作为示例,我们使用置换不变的 transformer-encoder 网络构建了 top 喷注和 QCD 喷注的数据表示,并可视化其对称性。我们通过线性分类器测试将 JetCLR 表示与其他表示进行比较,发现其效果相当好。
英文摘要:
Collider searches face the challenge of defining a representation of high-dimensional data such that physical symmetries are manifest, the discriminating features are retained, and the choice of representation is new-physics agnostic. We introduce JetCLR to solve the mapping from low-level data to optimized observables though self-supervised contrastive learning. As an example, we construct a data representation for top and QCD jets using a permutation-invariant transformer-encoder network and visualize its symmetry properties. We compare the JetCLR representation with alternative representations using linear classifier tests and find it to work quite well.
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。