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 2101.06428hep-excs.LG
收藏

用于带电粒子跟踪的散列和度量学习

Hashing and metric learning for charged particle tracking

Université de Genève(日内瓦大学);European Organization for Nuclear Research CERN(欧洲核子研究中心)

Sabrina Amrouche, Moritz Kiehn, Tobias Golling, Andreas Salzburger

摘要:

提出了一种基于近似近邻搜索的高能粒子对撞机带电粒子跟踪新方法。由于每次碰撞要重建数十万个测量结果,例如在高亮度大型强子对撞机上,目前采用的组合寻轨方法变得不够。在这里,我们使用散列技术将测量值分成20-50个命中的桶,并使用度量学习来提高它们的纯度。研究了两种不同的方法来进一步解析桶内的轨迹:局部Fisher判别分析和用于三元组相似性学习的神经网络。我们证明了所提出的方法在模拟碰撞,并显示显着的速度提高桶跟踪效率为96%和8%的假率看不见的粒子事件。

英文摘要:

We propose a novel approach to charged particle tracking at high intensity particle colliders based on Approximate Nearest Neighbors search. With hundreds of thousands of measurements per collision to be reconstructed e.g. at the High Luminosity Large Hadron Collider, the currently employed combinatorial track finding approaches become inadequate. Here, we use hashing techniques to separate measurements into buckets of 20-50 hits and increase their purity using metric learning. Two different approaches are studied to further resolve tracks inside buckets: Local Fisher Discriminant Analysis and Neural Networks for triplet similarity learning. We demonstrate the proposed approach on simulated collisions and show significant speed improvement with bucket tracking efficiency of 96% and a fake rate of 8% on unseen particle events.

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。

↑