Ultrafast jet classification at the HL-LHC

Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale with the input size and choice of algorithm. Moreover, the models proposed here are designed to work on the type of data and under the foreseen conditions at the CERN large hadron collider during its high-luminosity phase. Through quantization-aware training and efficient synthetization for a specific field programmable gate array, we show that O ( 100 ) ns inference of complex architectures such as Deep Sets and Interaction Networks is feasible at a relatively low computational resource cost.

Authors

Institutions

Publication Details

Journal
Repository for Publications and Research Data (ETH Zurich)
Published
2024-09-01
DOI
https://doi.org/10.3929/ethz-b-000685509
Citations
3
Primary Topic
Particle physics theoretical and experimental studies
Type
article
Field-Weighted Citation Impact
1.98

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Ultrafast jet classification at the HL-LHC

Vladimir Lončar, Zhiqiang Que, Wayne Luk, A. Tapper et al.
3 citations
Repository for Publications and Research Data (ETH Zurich)
Particle physics theoretical and experimental studies
1.98
article

Ultrafast jet classification at the HL-LHC

Vladimir Lončar, Zhiqiang Que, Wayne Luk, A. Tapper, A. Lobanov, Patrick Odagiu, Arpita Seksaria, Javier Mauricio Duarte, J. Ngadiuba, Sioni Summers, M. Pierini, J. Haller, Thea K Årrestad, G. Kasieczka, A. Sznajder, Philipp Rincke
article en
3 citations

Abstract

Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale with the input size and choice of algorithm. Moreover, the models proposed here are designed to work on the type of data and under the foreseen conditions at the CERN large hadron collider during its high-luminosity phase. Through quantization-aware training and efficient synthetization for a specific field programmable gate array, we show that O ( 100 ) ns inference of complex architectures such as Deep Sets and Interaction Networks is feasible at a relatively low computational resource cost.

Repository for Publications and Research Data (ETH Zurich)
Uppsala University (SE), Fermi National Accelerator Laboratory (US), Universität Hamburg (DE), ETH Zurich (CH), University of California San Diego (US), Universidade do Estado do Rio de Janeiro (BR), Universitätsmedizin Göttingen (DE), Institute of Physics Belgrade (RS), Imperial College London (GB), Massachusetts Institute of Technology (US), European Organization for Nuclear Research (CH)
National Science Foundation, U.S. Department of Energy, European Commission, Deutsche Forschungsgemeinschaft, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro, Universität Hamburg, Office of Science, Engineering and Physical Sciences Research Council, High Energy Physics
Decent work and economic growth
Openalex Percentile: Top 9%
Particle physics theoretical and experimental studies
1.98
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.