Search Results for author: Joosep Pata

Found 9 papers, 3 papers with code

Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors

no code implementations13 Sep 2023 Joosep Pata, Eric Wulff, Farouk Mokhtar, David Southwick, Mengke Zhang, Maria Girone, Javier Duarte

Efficient and accurate algorithms are necessary to reconstruct particles in the highly granular detectors anticipated at the High-Luminosity Large Hadron Collider and the Future Circular Collider.

Graph Neural Network

Progress towards an improved particle flow algorithm at CMS with machine learning

no code implementations30 Mar 2023 Farouk Mokhtar, Joosep Pata, Javier Duarte, Eric Wulff, Maurizio Pierini, Jean-Roch Vlimant

The particle-flow (PF) algorithm, which infers particles based on tracks and calorimeter clusters, is of central importance to event reconstruction in the CMS experiment at the CERN LHC, and has been a focus of development in light of planned Phase-2 running conditions with an increased pileup and detector granularity.

Graph Neural Network

Sensitivity Estimation for Dark Matter Subhalos in Synthetic Gaia DR2 using Deep Learning

no code implementations15 Mar 2022 Abdullah Bazarov, María Benito, Gert Hütsi, Rain Kipper, Joosep Pata, Sven Põder

The abundance of dark matter (DM) subhalos orbiting a host galaxy is a generic prediction of the cosmological framework, and is a promising way to constrain the nature of DM.

Anomaly Detection

Hyperparameter optimization of data-driven AI models on HPC systems

no code implementations2 Mar 2022 Eric Wulff, Maria Girone, Joosep Pata

This work exercises High Performance Computing resources to perform large-scale hyperparameter optimization using distributed training on multiple compute nodes.

Bayesian Optimization Graph Neural Network +1

Machine Learning for Particle Flow Reconstruction at CMS

no code implementations1 Mar 2022 Joosep Pata, Javier Duarte, Farouk Mokhtar, Eric Wulff, Jieun Yoo, Jean-Roch Vlimant, Maurizio Pierini, Maria Girone

The standard particle flow algorithm reconstructs stable particles based on calorimeter clusters and tracks to provide a global event reconstruction that exploits the combined information of multiple detector subsystems, leading to strong improvements for quantities such as jets and missing transverse energy.

BIG-bench Machine Learning Graph Neural Network

Explaining machine-learned particle-flow reconstruction

2 code implementations24 Nov 2021 Farouk Mokhtar, Raghav Kansal, Daniel Diaz, Javier Duarte, Joosep Pata, Maurizio Pierini, Jean-Roch Vlimant

The particle-flow (PF) algorithm is used in general-purpose particle detectors to reconstruct a comprehensive particle-level view of the collision by combining information from different subdetectors.

Decision Making Graph Neural Network

MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks

1 code implementation21 Jan 2021 Joosep Pata, Javier Duarte, Jean-Roch Vlimant, Maurizio Pierini, Maria Spiropulu

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum.

Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors

no code implementations25 Mar 2020 Xiangyang Ju, Steven Farrell, Paolo Calafiura, Daniel Murnane, Prabhat, Lindsey Gray, Thomas Klijnsma, Kevin Pedro, Giuseppe Cerati, Jim Kowalkowski, Gabriel Perdue, Panagiotis Spentzouris, Nhan Tran, Jean-Roch Vlimant, Alexander Zlokapa, Joosep Pata, Maria Spiropulu, Sitong An, Adam Aurisano, Jeremy Hewes, Aristeidis Tsaris, Kazuhiro Terao, Tracy Usher

Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision.

Instrumentation and Detectors High Energy Physics - Experiment Computational Physics Data Analysis, Statistics and Probability

Processing Columnar Collider Data with GPU-Accelerated Kernels

1 code implementation14 Jun 2019 Joosep Pata, Maria Spiropulu

At high energy physics experiments, processing billions of records of structured numerical data from collider events to a few statistical summaries is a common task.

Data Analysis, Statistics and Probability Distributed, Parallel, and Cluster Computing Computational Physics

Cannot find the paper you are looking for? You can Submit a new open access paper.