Physics and Computing Performance of the Exa.TrkX TrackML Pipeline

• URL: http://arxiv.org/abs/2103.06995v1
• Date: Thu, 11 Mar 2021 23:10:18 GMT
• Title: Physics and Computing Performance of the Exa.TrkX TrackML Pipeline
• Authors: Xiangyang Ju (1) and Daniel Murnane (1) and Paolo Calafiura (1) and Nicholas Choma (1) and Sean Conlon (1) and Steve Farrell (1) and Yaoyuan Xu (1) and Maria Spiropulu (2) and Jean-Roch Vlimant (2) and Adam Aurisano (3) and Jeremy Hewes (3) and Giuseppe Cerati (4) and Lindsey Gray (4) and Thomas Klijnsma (4) and Jim Kowalkowski (4) and Markus Atkinson (5) and Mark Neubauer (5) and Gage DeZoort (6) and Savannah Thais (6) and Aditi Chauhan (7) and Alex Schuy (7) and Shih-Chieh Hsu (7) and Alex Ballow (8) and and Alina Lazar (8) ((1) Lawrence Berkeley National Laboratory, (2) California Institute of Technology, (3) University of Cincinnati, (4) Fermi National Accelerator Laboratory, (5) University of Illinois at Urbana-Champaign, (6) Princeton University, (7) University of Washington, (8) Youngstown State University)
• Abstract summary: This paper documents developments needed to study the physics and computing performance of the Exa.TrkX pipeline. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. The Exa.TrkX tracking pipeline clusters detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-like tracking detector), has been demonstrated on various detectors, including the DUNE LArTPC and the CMS High-Granularity Calorimeter. This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS and CMS data. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms. Crucially for future HEP applications, the pipeline benefits significantly from GPU acceleration, and its computational requirements scale close to linearly with the number of particles in the event.

Related papers

• Pre-training on Synthetic Driving Data for Trajectory Prediction [61.520225216107306]
  We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. We adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. We conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies.
  arXiv  Detail & Related papers  (2023-09-18T19:49:22Z)
• PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks [68.96484488899901]
  We present PARTIME, a library designed to speed up neural networks whenever data is continuously streamed over time. PARTIME starts processing each data sample at the time in which it becomes available from the stream. Experiments are performed in order to empirically compare PARTIME with classic non-parallel neural computations in online learning.
  arXiv  Detail & Related papers  (2022-10-17T14:49:14Z)
• Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines [27.461398584509755]
  DataScope is the first system that efficiently computes Shapley values of training examples over an end-to-end machine learning pipeline. Our results show that DataScope is up to four orders of magnitude faster than state-of-the-art Monte Carlo-based methods.
  arXiv  Detail & Related papers  (2022-04-23T19:29:23Z)
• Machine Learning for Particle Flow Reconstruction at CMS [7.527568379083754]
  We provide details on the implementation of a machine-learning based particle flow algorithm for CMS. The algorithm reconstructs stable particles based on calorimeter clusters and tracks to provide a global event reconstruction.
  arXiv  Detail & Related papers  (2022-03-01T10:11:44Z)
• Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines [77.45213180689952]
  Preprocessing pipelines in deep learning aim to provide sufficient data throughput to keep the training processes busy. We introduce a new perspective on efficiently preparing datasets for end-to-end deep learning pipelines. We obtain an increased throughput of 3x to 13x compared to an untuned system.
  arXiv  Detail & Related papers  (2022-02-17T14:31:58Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Graph Neural Networks for Charged Particle Tracking on FPGAs [2.6402980149746913]
  The determination of charged particle trajectories in collisions at the CERN Large Hadron Collider (LHC) is an important but challenging problem. Graph neural networks (GNNs) are a type of geometric deep learning algorithm that has successfully been applied to this task. We introduce an automated translation workflow, integrated into a broader tool called $textthls4ml$, for converting GNNs into firmware for field-programmable gate arrays (FPGAs)
  arXiv  Detail & Related papers  (2021-12-03T17:56:10Z)
• Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans [103.92680099373567]
  This paper introduces a pipeline to parametrically sample and render multi-task vision datasets from comprehensive 3D scans from the real world. Changing the sampling parameters allows one to "steer" the generated datasets to emphasize specific information. Common architectures trained on a generated starter dataset reached state-of-the-art performance on multiple common vision tasks and benchmarks.
  arXiv  Detail & Related papers  (2021-10-11T04:21:46Z)
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks [0.0]
  In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a particle-level view of the event. We introduce a novel, end-to-end trainable, machine-learned particle-flow algorithm based on parallelizable, scalable, and graph neural networks. We report the physics and computational performance of the algorithm on a Monte Carlo dataset of top quark-antiquark pairs produced in proton-proton collisions.
  arXiv  Detail & Related papers  (2021-01-21T12:47:54Z)
• Faster object tracking pipeline for real time tracking [0.0]
  Multi-object tracking (MOT) is a challenging practical problem for vision based applications. This paper showcases a generic pipeline which can be used to speed up detection based object tracking methods.
  arXiv  Detail & Related papers  (2020-11-08T06:33:48Z)
• A DICOM Framework for Machine Learning Pipelines against Real-Time Radiology Images [50.222197963803644]
  Niffler is an integrated framework that enables the execution of machine learning pipelines at research clusters. Niffler uses the Digital Imaging and Communications in Medicine (DICOM) protocol to fetch and store imaging data. We present its architecture and three of its use cases: an inferior vena cava filter detection from the images in real-time, identification of scanner utilization, and scanner clock calibration.
  arXiv  Detail & Related papers  (2020-04-16T21:06:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.