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 2606.20437hep-excs.LG
收藏

HEPTv2:用于带电粒子重建的端到端高效点变换器

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

School of Electrical and Computer Engineering, Georgia Institute of Technology(佐治亚理工学院电气与计算机工程学院);Department of Physics and Astronomy, Purdue University(普渡大学物理与天文学系);Department of Physics, University of California San Diego(加州大学圣地亚哥分校物理系);Department of Physics, University of Washington(华盛顿大学物理系)

Siqi Miao, Shitij Govil, Jack P. Rodgers, Mia Liu, Javier Duarte, Shih-Chieh Hsu, Yuan-Tang Chou, Pan Li

AI总结:

提出HEPTv2,一种端到端点变换器架构,通过局部敏感哈希编码和扇区化解码,无需图构建即可从探测器击中点直接重建粒子轨迹,在TrackML上以0.8%假率实现98.6%追踪效率,延迟仅15ms。

摘要:

带电粒子追踪——从稀疏探测器测量中重建轨迹——是一个基础的高能物理推理问题,也是在极端组合歧义下学习的典型例子。在高亮度大型强子对撞机(HL-LHC)上,尽管碰撞密度前所未有,追踪必须保持准确和高效。图神经网络表现强劲,但图构建和处理带来了大量成本,而基于变换器的方法依赖辅助阶段,阻碍了端到端优化。为解决这一问题,我们提出了HEPTv2,一种端到端点变换器架构,在一个可训练管道中从探测器击中点重建轨迹。HEPTv2结合了局部感知点编码器和轨迹解码器,无需图构建、聚类或过滤即可预测完整轨迹。编码器在探测器坐标空间中使用局部敏感哈希,以保留追踪相关几何结构,同时实现高效的局部注意力。解码器通过扇区化解码和联合编码器-解码器监督下的直接击中到轨迹预测来消除歧义,使整个管道能够端到端优化。在TrackML上,HEPTv2以0.8%的假率实现了98.6%的双多数追踪效率,同时在NVIDIA A100 GPU上每个事件仅需约15毫秒推理时间和0.4 GB峰值内存。对于最多包含$5\ imes10^5$个击中点的事件,延迟和内存大致线性扩展。HEPTv2在精度-延迟权衡中建立了新的最先进水平,相比之前最强的变换器效率提升4.5%,相比优化的基于图管道提升1.1-2.2%,同时延迟分别降低7倍和38-52倍。这些结果表明,端到端变换器能够提供HL-LHC实时粒子重建所需的精度和效率。

英文摘要:

Charged-particle tracking -- reconstructing trajectories from sparse detector measurements -- is a fundamental high-energy-physics inference problem and a canonical example of learning under extreme combinatorial ambiguity. At the High-Luminosity Large Hadron Collider (HL-LHC), tracking must remain accurate and efficient despite unprecedented collision densities. Graph neural networks perform strongly, but incur substantial costs from graph construction and processing, while transformer-based approaches rely on auxiliary stages that prevent end-to-end optimization. To address this, we present HEPTv2, an end-to-end point-transformer architecture that reconstructs tracks from detector hits in one trainable pipeline. HEPTv2 combines a locality-aware point encoder with a track decoder that predicts complete trajectories without graph-building, clustering, or filtering. The encoder uses locality-sensitive hashing in detector coordinate space to preserve tracking-relevant geometry while enabling efficient local attention. The decoder resolves ambiguities through sectorized decoding and direct hit-to-track prediction under joint encoder-decoder supervision, allowing the full pipeline to be optimized end-to-end. On TrackML, HEPTv2 achieves 98.6% double-majority tracking efficiency at a 0.8% fake rate, while requiring only $\sim$15~ms inference time and 0.4~GB peak memory per event on a NVIDIA A100 GPU. Latency and memory scale approximately linearly for events with up to $5\times10^5$ hits. HEPTv2 establishes a new state of the art in the accuracy-latency trade-off, improving efficiency by 4.5% over the strongest prior transformer and by 1.1--2.2% over optimized graph-based pipelines, while reducing latency by factors of 7 and 38--52, respectively. These results show end-to-end transformers can deliver the accuracy and efficiency required for real-time particle reconstruction at the HL-LHC.

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。

↑