Jump to: Fellows - Projects - Presentations - Publications - Videos

Innovative Algorithms

Algorithms to perform the real-time processing in the trigger and the reconstruction of both real and simulated detector data are critical components of HEP’s computing challenge. These algorithms face a number of new challenges in the next decade due to new and upgraded accelerator facilities, detector upgrades and new detector technologies, increases in anticipated event rates, and emerging computing architectures. Projects in the IA area are focussed in three areas:

Developing tracking algorithms for the HL-LHC
Re-engineering algorithms for hardware accelerators
Exploiting major advances in machine learning

Tracking for the HL-LHC is an area in particular need of novel approaches as it is expected to require a large fraction of the CPU budget. IA is working to develop more efficient and performant tracking algorithms. Hardware accelerators are expected to be the way forward to speed up reduce infrastructure cost. IA is exploring the use of hardware accelerators for tracking and the use of ML on accelerators in realistic HEP applications. In the area of machine learning, IA aims to capitalize on industry and data science techniques and tools. In particular, we are investigating new HEP applications of ML and to apply new ML techniques to HEP.

Contact us: ia-team@iris-hep.org

Markus Atkinson

Gowtham Atluri

Daniel Craik

Kyle Cranmer

Peter Elmer

Irina Espejo

Louis-Guillaume Gagnon

Rocky Bala Garg

Heather Gray

Philip Harris

Slava Krutelyov

Sebastian Macaluso

Dylan Rankin

Marian Stahl

Matevz Tadel

Savannah Thais

Lauren Tompkins

Carlo Varni

Bei Wang

Mike Williams

Peter Wittich

Avi Yagil

Beomki Yeo

Current and Previous IA Fellows

Abdelrahman Elabd

Alan Aneeth Jegaraj

Aneesh Heintz

Caitlin Patterson

Emily Tsai

Garima Singh

Jeremy Ferguson

Omar Alterkait

Orgho Neogi

Peter Chatain

Raghav Kansal

Ralf Farkas

Sammy Edwards

Sean Condon

Sofia Graziano

Tomohiro Yamazaki

Varun Sreenivasan

Vesal Razavimaleki

IA Projects

Accelerated GNN Tracking
accel-gnn-tracking
More information

Accelerators and ML for reconstruction
Accelerated calorimeter reconstruction using Machine Learning as a Service
More information

ACTS
Development of experiment-independent, thread-safe track reconstruction.
More information

exploratory-ml
Analysis Reinterpretation
More information

GPU Trigger Project
Allen: a GPU trigger for LHCb
More information

Line-Segment tracking
Segment linking tracking for CMS
More information

Machine Learning for jets
Machine learning for jets
More information

mkFit
Modernizing Kalman filter tracking for CMS
More information

PV-Finder
CNNs to find primary vertices
More information

IA Presentations

20 May 2021 - "Reframing Jet Physics with New Computational Methods", Sebastian Macaluso, 25th International Conference on Computing in High Energy & Nuclear Physics
17 May 2021 - "Perspective on HEP Software", Heather Gray, vCHEP
5 May 2021 - "Explorations at the Physics ∩ ML Interface", Kyle Cranmer, Physics ∩ ML seminar series
26 Apr 2021 - "An AI revolution in science? Using machine learning for scientific discovery", Kyle Cranmer, University of Cambridge Accelerate Programme for Scientific Discovery
25 Mar 2021 - "Graph Deep Learning for Physics", Kyle Cranmer, Università della Svizzera
1 Mar 2021 - "Reframing Jet Physics in Probabilistic Terms", Sebastian Macaluso, CCPP Brown Bag seminar, NYU
26 Feb 2021 - "Parameter Optimization and Layer Linking in ACTS track Seeding", Rocky Bala Garg, ACTS Machine Learning Meeting
22 Feb 2021 - "Quarks, hierarchical clustering, and combinatorial optimization", Kyle Cranmer, Deep Learning and Combinatorial Optimization
18 Feb 2021 - "MadMiner tutorial", Kyle Cranmer, (Re)interpreting the results of new physics searches at the LHC
12 Feb 2021 - "Athena-ACTS Wrapper: Iterative Vertex Finder with Full Billoir Fitter", Rocky Bala Garg, SLAC ATLAS meeting
18 Dec 2020 - "Some fun examples from the intersection of machine learning and physics", Kyle Cranmer, ML in PL
15 Dec 2020 - "Accelerated Strip Local reconstruction on GPUs", Dan Riley, CMS Tracker Detector Performance Group
8 Dec 2020 - "How machine learning can help us get the most out of our highest fidelity physical models", Kyle Cranmer, AI for Atoms
7 Dec 2020 - "Segment Linking Development on GPUs", Michael (Tres) Reid, HLT developments with GPUs
4 Dec 2020 - "Workshop Overview and Goals", Mark Neubauer, Mini-Workshop on Portable Inference
30 Nov 2020 - "Hough Transforms and GNN", Markus Atkinson, Exa.Trkx Weekly Meeting

[expand]

30 Nov 2020 - "Hough Transforms and GNN", Markus Atkinson, Exa.Trkx Weekly Meeting
2 Nov 2020 - "Tracking with GNN", Savannah Thais, CMS Tracking POG meeting (CMS internal)
23 Oct 2020 - "Graph Neural Networks Architectures", Markus Atkinson, FastML Co-processors Meeting
21 Oct 2020 - "Accelerated Pixed Detector Tracklet Finding with GNNs on FPGAS", Savannah Thais, 4th Annual Inter-Experiment Machine Learning Workshop
21 Oct 2020 - "Graph Neural Networks Architectures", Markus Atkinson, IRIS-HEP Topical Meeting
19 Oct 2020 - "mkFit report: plans for offline tracking in Run3", Slava Krutelyov, CMS Tracking POG Meeting (CMS restricted)
6 Oct 2020 - "mkFit report: plans for offline tracking in Run3", Slava Krutelyov, CMS Tracker DPG - Tracking POG General Meeting (CMS restricted)
30 Sep 2020 - "GNNs for Tracking", Savannah Thais, CMS Machine Learning Forum
24 Sep 2020 - "How machine learning can help us get the most out of our highest fidelity physical models", Kyle Cranmer, NYU Physics Colloquium
22 Sep 2020 - "Reusable Workflows, active learning, and simulation-based inference", Kyle Cranmer, UCI Symposium on Reproducibility in Machine Learning
21 Sep 2020 - "New Computational Techniques and Machine Learning for Jet Physics", Sebastian Macaluso, Particle Theory Seminar, Instituto de Fisica La Plata, UNLP
9 Sep 2020 - "Using GPUs and FPGAs as-a-service for LHC computing", Dylan Rankin, IRIS-HEP topical meeting
2 Sep 2020 - "Ambiguity Resolution in ACTS", Irina Ene, IRIS-HEP topical meeting
26 Aug 2020 - "Initial studies of ACTS tracking performance with GPUs", Xiaocong Ai, IRIS-HEP Topical meeting
11 Aug 2020 - "Particle Physics and Machine Learning in Education", Mark Neubauer, Snowmass Computational Frontier Workshop
11 Aug 2020 - "IRIS-HEP Report: Innovative Algorithms", Heather Gray, Snowmass Computational Frontier Workshop
5 Aug 2020 - "mkFit update: strip tracker unpacking and clustering on GPU ", Dan Riley, CMS Strip Calibration and Local Reconstruction Meeting
21 Jul 2020 - "How machine learning can help us get the most out of our highest fidelity physical models", Kyle Cranmer, Machine Learning in Science 2020
17 Jul 2020 - "Graphs, Trees, and Sets: structured data in physics", Kyle Cranmer, ICML Workshop on Graph Representation Learning
17 Jul 2020 - "Likelihood-based models for Simulation-based Inference", Kyle Cranmer, ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models
8 Jul 2020 - "How machine learning can help us get the most out of our highest fidelity physical models", Kyle Cranmer, ELLIS SOCIETY: AI4Science Kickoff Workshop
2 Jul 2020 - "The interplay of Math, Physics, and Machine Learning", Kyle Cranmer, IST seminar series Mathematics, Physics & Machine Learning
9 Jun 2020 - "Local tracker reconstruction on accelerators", Dan Riley, CMS Upgrade R&D/CMP Meeting
31 May 2020 - "How machine learning can help us get the most out of our highest fidelity physical models", Kyle Cranmer, Tel Aviv University Physics Department Colloquium
29 May 2020 - "Future Blueprint Topics: Year 3 Plans, 4 and 5 Year Thoughts", Mark Neubauer, IRIS-HEP Team Retreat
29 May 2020 - "Summary of Wednesday Session: Core Developments", Xiaocong Ai, ACTS Tracking for HEP Workshop
28 May 2020 - "ACTS Propagation on GPUs", Xiaocong Ai, ACTS Tracking for HEP Workshop
26 May 2020 - "ACTS Track fitting/finding Tutorial", Xiaocong Ai, ACTS Tracking for HEP Workshop
26 May 2020 - "Innovative Algorithms - Years 3, and 4+5", David Lange, IRIS-HEP team retreat
25 May 2020 - "ACTS Project Status", Xiaocong Ai, ACTS Tracking for HEP Workshop
18 May 2020 - "Graph Neural Network Tracking using the Endcaps", Markus Atkinson, Exa.Trkx Weekly Meeting
15 May 2020 - "Acts Integration into Athena", Rocky Bala Garg, SLAC ATLAS meeting
7 May 2020 - "How machine learning can help us get the most out of our highest fidelity physical models", Kyle Cranmer, MIT Physics Department Colloquium
5 May 2020 - "mkFit update: strip tracker unpacking and clustering on GPU", Dan Riley, CMS HLT Upgrade TSG Weekly Meeting
4 May 2020 - "Pixel Detector Tracklet Finding", Markus Atkinson, Exa.Trkx Weekly Meeting
28 Apr 2020 - "mkFit update: strip tracker unpacking and clustering on GPU", Dan Riley, CMS Tracker DPG - Tracking POG general Weekly Meeting
26 Apr 2020 - "Autoencoders for Compression and Simulation in Particle Physics", Daniel Craik, International Conference on Learning Representations 2020
22 Apr 2020 - "Parallelizing the unpacking and clustering of detector data for reconstruction of charged particle tracks on multi-core CPUs and many-core GPUs", Bei Wang, Connecting The Dots (2020)
22 Apr 2020 - "Tracking performance with ACTS", Xiaocong Ai, Connecting The Dots 2020
20 Apr 2020 - "An updated hybrid deep learning algorithm for identifying and locating primary vertices", Marian Stahl, Connecting The Dots 2020
20 Apr 2020 - "Connecting the Dots 2020 - Workshop introduction", David Lange, Connecting the Dots 2020
5 Mar 2020 - "Artifical Intelligence for High-Energy Physics", Mark Neubauer, Artificial Intelligence for Nuclear Physics Workshop
5 Mar 2020 - "Challenges and Evolution of the LHC computing model for HL-LHC", David Lange, Boston University seminar
5 Mar 2020 - "Machine Learning and Physics", Kyle Cranmer, Special QU-PCD Colloquium at DESY (CANCELED due to COVID19)
3 Mar 2020 - "Machine Learning for Effective Field Theories", Kyle Cranmer, PREFIT20: PRecision Effective FIeld Theory School
27 Feb 2020 - "New Algorithms and Computing Architectures for Tracking", Savannah Thais, IRIS-HEP 18 Month Review
27 Feb 2020 - "GNN Tracking and FPGA Acceleration (poster)", Markus Atkinson, IRIS-HEP Poster Session
27 Feb 2020 - "Allen: a GPU trigger for LHCb", Daniel Craik, IRIS-HEP Poster Session
19 Feb 2020 - "Track fitting/finding with ACTS", Xiaocong Ai, Iris-hep topical meeting
12 Feb 2020 - "mkfit and HL-LHC tracking in CMS", Mario Masciovecchio, Joint HSF event reconstruction/trigger working group and IRIS-HEP Topical Meeting
11 Feb 2020 - "Accelerated Full Tracking at (CMS) HLT", Mario Masciovecchio, CMS scouting kick-off workshop
5 Feb 2020 - "mkFit update: strip tracker unpacking and clustering on CPU and GPU", Dan Riley, CMS Tracker DPG/Strip Calibration and Local Reconstruction Weekly Meeting
29 Jan 2020 - "LHCb HLT performance- and regression-tests A hybrid deep learning approach to vertexing", Marian Stahl, IRIS-HEP Topical Meeting
27 Jan 2020 - "The Allen Project", Daniel Craik, IRIS-HEP Topical Meeting
17 Jan 2020 - "Looking into Jets with Machine Learning", Sebastian Macaluso, ML4Jets 2020
17 Jan 2020 - "ROB: Reproducible Open Benchmarks for Data Analysis Platform", Heiko Mueller, ML4Jets 2020
17 Jan 2020 - "A Worldwide Software Collaboration?", David Lange, Hong Kong IAS Mini-workshop: Experiment / Detector - Software and Physics Requirements for e+e- Colliders
16 Dec 2019 - "Update on mkFit developments", Slava Krutelyov, CMS Tracking POG Meeting (CMS restricted)
9 Dec 2019 - "The Trigger and Real-time Reconstruction at LHCb", Daniel Craik, CPAD Instrumentation Frontier Workshop 2019
22 Nov 2019 - "Reconstruction R&D for HEP in the next decade", Slava Krutelyov, Latin American Workshop on Software and Computing challenges in High-Energy Particle Physics (LAWSCHEP 2019)
19 Nov 2019 - "Looking into Jets with Machine Learning", Sebastian Macaluso, Particle Theory Seminar, Harvard University
19 Nov 2019 - "Flows three ways", Kyle Cranmer, Deep Learning for Physics Seminar Series at Princeton Center for Theoretical Physics
4 Nov 2019 - "Looking into Jets with Machine Learning", Sebastian Macaluso, Data Science Tea UMass
1 Nov 2019 - "Looking into Jets with Machine Learning", Sebastian Macaluso, NYU Physics x ML
19 Oct 2019 - "FPGA ML inference as a service on AWS", Markus Atkinson, FastML Co-processors Meeting
17 Oct 2019 - "Simulation-based inference, interpretability, and experimental design", Kyle Cranmer, Workshop on Interpretable Learning in Physical Sciences Part of the Long Program Machine Learning for Physics and the Physics of Learning
16 Oct 2019 - "Semantic Segmentation for CMS Pixel Clustering", Savannah Thais, US LHC Users' Association Meeting
16 Oct 2019 - "LHCb Status and Outlook", Daniel Craik, LHC Users Association Annual Meeting 2019
5 Oct 2019 - "Particle Physics in the context of Data Science", Kyle Cranmer, The 6th IEEE International Conference on Data Science and Advanced Analytics
30 Sep 2019 - "What does the Revolution in Artificial Intelligence Mean for Physics?", Kyle Cranmer, Joint PITT-CMU Physics Department Colloquium
27 Sep 2019 - "Simulation-based inference, causality, and active learning", Kyle Cranmer, AI and the Scientific Method, ETH, Zurich
25 Sep 2019 - "Benchmarks for ML4Jets research", Sebastian Macaluso, IRIS-HEP Topical Meeting
25 Sep 2019 - "Benchmarks for ML4Jets research", Heiko Mueller, IRIS-HEP Topical Meeting
24 Sep 2019 - "Looking into Jets with Machine Learning", Sebastian Macaluso, Princeton Pheno & Vino Seminar
13 Sep 2019 - "Histogramming and more", Henry Schreiner, 2019 IRIS-HEP Institute Retreat
12 Sep 2019 - "Introduction and Plans", Savannah Thais, IRIS-HEP Institute Retreat
12 Sep 2019 - "Introduction and Plans", Markus Atkinson, IRIS-HEP Institute Retreat
9 Sep 2019 - "The interplay between physically motivated simulations and machine learning", Kyle Cranmer, Machine Learning for Physics and the Physics of Learning Long Program at IPAM
8 Aug 2019 - "ACTS Status", Xiaocong Ai, USATLAS Summer Workshop
31 Jul 2019 - "Ambiguity Resolution: Using Machine Learning", Nicholas Cinko, ACTS Developers Meetings
31 Jul 2019 - "ACTS: a common track reconstruction software", Xiaocong Ai, DPF 2019
31 Jul 2019 - "Overview and Future directions for ML in particle and astro physics", Kyle Cranmer, Hammers & Nails 2019
25 Jul 2019 - "Introduction to Performance Tuning & Optimization Tools", Bei Wang, Third Computational and Data Science school for HEP (CoDaS-HEP 2019)
25 Jul 2019 - "Vector Parallelism on Multi-Core Processors", Steve Lantz, Third Computational and Data Science school for HEP (CoDaS-HEP 2019)
24 Jul 2019 - "Floating Point Arithmetic Is Not Real", Bei Wang, Third Computational and Data Science school for HEP (CoDaS-HEP 2019)
23 Jul 2019 - "The Machine Learning Landscape of Top Taggers", Sebastian Macaluso, 11th International Workshop on Boosted Object Phenomenology, Reconstruction and Searches in HEP (BOOST 2019)
24 Jun 2019 - "Future areas of focus for ML in particle physics", Kyle Cranmer, ATLAS Software and Computing Week
19 Jun 2019 - "SCAILFIN: Reproducible Open Benchmarks", Sebastian Macaluso, Analysis Systems Topical Meeting
19 Jun 2019 - "SCAILFIN: Reproducible Open Benchmarks", Heiko Mueller, Analysis Systems Topical Meeting
14 Jun 2019 - "Advances in Deep Learning motivated by Physics Problems", Kyle Cranmer, Theoretical Physics for Deep Learning
4 Jun 2019 - "Deep Learning for Higgs Boson Identification and Searches for New Physics at the Large Hadron Collider", Mark Neubauer, Blue Waters Symposium for Petascale Science and Beyond
29 May 2019 - "Machine learning in high-energy particle physics experiments, from simulation, through reconstruction to physics analysis", Heather Gray, Physics in Machine Learning Workshop
29 May 2019 - "The Primacy of Experiment", Kyle Cranmer, The Universe Speaks in Numbers
1 May 2019 - "Future areas of focus for ML in particle physics", Kyle Cranmer, Gotham City Physics X ML
17 Apr 2019 - "A hybrid deep learning approach to vertexing", Henry Schreiner, 3rd IML Machine Learning Workshop
15 Apr 2019 - "Future areas of focus for ML in particle physics", Kyle Cranmer, 3rd IML Machine Learning Workshop
5 Apr 2019 - "Scalable Cyberinfrastructure for Artificial Intelligence and Likelihood-Free Inference", Mark Neubauer, NSF Large Facilities Workshop
3 Apr 2019 - "A hybrid deep learning approach to vertexing", Henry Schreiner, Connecting The Dots and Workshop on Intelligent Trackers 2019
20 Mar 2019 - "Machine Learning for the Primary Vertex reconstruction", Henry Schreiner, 2019 Joint HSF/OSG/WLCG Workshop
11 Mar 2019 - "A hybrid deep learning approach to vertexing", Henry Schreiner, 19th International Workshop on Advanced Computing and Analysis Techniques in Physics Research
17 Feb 2019 - "Selected recent ideas in computing and their impact on high-energy physics", Heather Gray, 25th ICEPP Symposium
13 Feb 2019 - "Using ML on FPGAs to enhance reconstruction output", Dylan Rankin, IRIS-HEP Topical Meeting
6 Feb 2019 - "IRIS-HEP Innovative Algorithms", David Lange, IRIS-HEP Steering Board Meeting
6 Feb 2019 - "IRIS-HEP Innovative Algorithms", Heather Gray, IRIS-HEP Steering Board Meeting
13 Jan 2019 - "Ambiguity Resolution Studies with ACTS", Nicholas Cinko, Berkeley Tracking Workshop
13 Jan 2019 - "Workshop introduction", Heather Gray, Berkeley Tracking Workshop
13 Jan 2019 - "Ambiguity Resolution Studies with ACTS", Heather Gray, Berkeley Tracking Workshop
15 Nov 2018 - "Pulling Out All the Tops with Computer Vision and Deep Learning", Sebastian Macaluso, Machine Learning for Jet Physics
19 Oct 2018 - "Design Roadmap for Future Collaborations", Mark Neubauer, Deep Learning for Multimessenger Astrophysics Real-time Discovery at Scale

[/expand]

IA Publications

A GPU-based Kalman Filter for Track Fitting, X. Ai, G. Mania, H. Gray, M. Kuhn and N. Styles, arXiv 2105.01796 (04 May 2021).
The Tracking Machine Learning challenge : Throughput phase, S. Amrouche et. al., arXiv 2105.01160 (03 May 2021).
Exact and Approximate Hierarchical Clustering Using A*, C. Greenberg, S. Macaluso, N. Monath, A. Dubey, P. Flaherty, M. Zaheer, A. Ahmed, K. Cranmer and A. Mccallum, arXiv 2104.07061 (14 Apr 2021).
Charged particle tracking via edge-classifying interaction networks, G. Dezoort, S. Thais, I. Ojalvo, P. Elmer, V. Razavimaleki, J. Duarte, M. Atkinson and M. Neubauer, arXiv 2103.16701 (30 Mar 2021) [1 citation].
Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC, S. Thais and G. DeZoort, arXiv 2103.06509 (21 Mar 2021).
Physics and Computing Performance of the Exa.TrkX TrackML Pipeline, X. Ju et. al., arXiv 2103.06995 (11 Mar 2021) [1 citation].
Progress in developing a hybrid deep learning algorithm for identifying and locating primary vertices, S. Akar, G. Atluri, T. Boettcher, M. Peters, H. Schreiner, M. Sokoloff, M. Stahl, W. Tepe, C. Weisser and M. Williams, arXiv 2103.04962 (08 Mar 2021).
A deep search for decaying dark matter with XMM-Newton blank-sky observations, J. Foster, M. Kongsore, C. Dessert, Y. Park, N. Rodd, K. Cranmer and B. Safdi, arXiv 2102.02207 (03 Feb 2021) [4 citations].
Introduction to Normalizing Flows for Lattice Field Theory, M. Albergo, D. Boyda, D. Hackett, G. Kanwar, K. Cranmer, S. Racanière, D. Rezende and P. Shanahan, arXiv 2101.08176 (20 Jan 2021) [1 citation].
Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs, A. Heintz et. al., arXiv 2012.01563 (30 Nov 2020) [7 citations].
Hierarchical clustering in particle physics through reinforcement learning, J. Brehmer, S. Macaluso, D. Pappadopulo and K. Cranmer, arXiv 2011.08191 (16 Nov 2020).
Semi-parametric gamma-ray modeling with Gaussian processes and variational inference, S. Mishra-Sharma and K. Cranmer, arXiv 2010.10450 (20 Oct 2020) [1 citation].
FPGAs-as-a-Service Toolkit (FaaST), D. Rankin et. al., arXiv 2010.08556 (16 Oct 2020) [4 citations].
Simulation-based inference methods for particle physics, J. Brehmer and K. Cranmer, arXiv 2010.06439 (13 Oct 2020) [1 citation].
Snowmass 2021 Letter of Interest: Emerging Computational Techniques for Jet Physics, Sebastian Macaluso, Kyle Cranmer, Matthew Drnevich, Johann Brehmer (New York University); Duccio Pappadopulo (N.A.); Atılım Gunes Baydin (Oxford); Matthew Schwartz (Harvard), Snowmass 2021 Letters of Interest (31 Aug 2020).
Snowmass 2021 Letter of Interest: Fast Machine Learning, M.-A. Flechas, M. Atkinson, G.-Di Guglielmo, J. Duarte, F. Fahim, P. Harris, C. Herwig, B. Holzman, R. Kastner, M. Liu, C.-S. Moon, M. Neubauer, K. Pedro, A.-Q. Parra, D. Rankin, R. Rivera, N. Tran, M. Wang, T. Yang, J. Agar9, and E.-A. Huerta, Snowmass 2021 Letters of Interest (31 Aug 2020).