Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.07594 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909942540140544 |
|---|---|
| author | Govil, Shitij Rodgers, Jack P. Chou, Yuan-Tang Miao, Siqi Saha, Amit Anand, Advaith Lieret, Kilian DeZoort, Gage Liu, Mia Duarte, Javier Li, Pan Hsu, Shih-Chieh |
| author_facet | Govil, Shitij Rodgers, Jack P. Chou, Yuan-Tang Miao, Siqi Saha, Amit Anand, Advaith Lieret, Kilian DeZoort, Gage Liu, Mia Duarte, Javier Li, Pan Hsu, Shih-Chieh |
| contents | Charged particle track reconstruction is a foundational task in collider experiments and the main computational bottleneck in particle reconstruction. Graph neural networks (GNNs) have shown strong performance for this problem, but costly graph construction, irregular computations, and random memory access patterns substantially limit their throughput. The recently proposed Hashing-based Efficient Point Transformer (HEPT) offers a theoretically guaranteed near-linear complexity for large point cloud processing via locality-sensitive hashing (LSH) in attention computations; however, its evaluations have largely focused on embedding quality, and the object condensation pipeline on which HEPT relies requires a post-hoc clustering step (e.g., DBScan) that can dominate runtime. In this work, we make two contributions. First, we present a unified, fair evaluation of physics tracking performance for HEPT and a representative GNN-based pipeline under the same dataset and metrics. Second, we introduce HEPTv2 by extending HEPT with a lightweight decoder that eliminates the clustering stage and directly predicts track assignments. This modification preserves HEPT's regular, hardware-friendly computations while enabling ultra-fast end-to-end inference. On the TrackML dataset, optimized HEPTv2 achieves approximately 28 ms per event on an A100 while maintaining competitive tracking efficiency. These results position HEPTv2 as a practical, scalable alternative to GNN-based pipelines for fast tracking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07594 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Locality-Sensitive Hashing-Based Efficient Point Transformer for Charged Particle Reconstruction Govil, Shitij Rodgers, Jack P. Chou, Yuan-Tang Miao, Siqi Saha, Amit Anand, Advaith Lieret, Kilian DeZoort, Gage Liu, Mia Duarte, Javier Li, Pan Hsu, Shih-Chieh High Energy Physics - Experiment Machine Learning Charged particle track reconstruction is a foundational task in collider experiments and the main computational bottleneck in particle reconstruction. Graph neural networks (GNNs) have shown strong performance for this problem, but costly graph construction, irregular computations, and random memory access patterns substantially limit their throughput. The recently proposed Hashing-based Efficient Point Transformer (HEPT) offers a theoretically guaranteed near-linear complexity for large point cloud processing via locality-sensitive hashing (LSH) in attention computations; however, its evaluations have largely focused on embedding quality, and the object condensation pipeline on which HEPT relies requires a post-hoc clustering step (e.g., DBScan) that can dominate runtime. In this work, we make two contributions. First, we present a unified, fair evaluation of physics tracking performance for HEPT and a representative GNN-based pipeline under the same dataset and metrics. Second, we introduce HEPTv2 by extending HEPT with a lightweight decoder that eliminates the clustering stage and directly predicts track assignments. This modification preserves HEPT's regular, hardware-friendly computations while enabling ultra-fast end-to-end inference. On the TrackML dataset, optimized HEPTv2 achieves approximately 28 ms per event on an A100 while maintaining competitive tracking efficiency. These results position HEPTv2 as a practical, scalable alternative to GNN-based pipelines for fast tracking. |
| title | Locality-Sensitive Hashing-Based Efficient Point Transformer for Charged Particle Reconstruction |
| topic | High Energy Physics - Experiment Machine Learning |
| url | https://arxiv.org/abs/2510.07594 |