5th Inter-experiment Machine Learning Workshop

Session

Workshop

Workshop

10 May 2022, 16:05

500/1-001 - Main Auditorium (CERN)

Conveners

Workshop: Jets and simulations

• Michael Aaron Kagan (SLAC National Accelerator Laboratory (US))
• Riccardo Torre (CERN)

Workshop: Uncertainty-aware learning, invertible networks, and anomaly detection in DQM

• Pietro Vischia (Universite Catholique de Louvain (UCL) (BE))
• Simon Akar (University of Cincinnati (US))

Workshop: Neural ratio estimators, Autoencoders, Orsay workshop summary

• Simon Akar (University of Cincinnati (US))
• Fabio Catalano (University and INFN Torino (IT))

Workshop: Simulation-based inference, neural ratio estimates, end-to-end reconstruction, anomaly detection

• Simon Akar (University of Cincinnati (US))
• Fabio Catalano (University and INFN Torino (IT))

Workshop: Generative Models

• Michael Aaron Kagan (SLAC National Accelerator Laboratory (US))
• Riccardo Torre (CERN)

Workshop: ML in theory and phenomenology

• Michael Aaron Kagan (SLAC National Accelerator Laboratory (US))
• Riccardo Torre (CERN)

Workshop: Generative models, and identification algorithms

• Anja Butter
• Fabio Catalano (University and INFN Torino (IT))

Workshop: Fast and real-time inference

• Fabio Catalano (University and INFN Torino (IT))
• Anja Butter

Workshop: ML as a service, QML, reconstruction

• Simon Akar (University of Cincinnati (US))
• Fabio Catalano (University and INFN Torino (IT))

Workshop: Reconstruction and identification

• Fabio Catalano (University and INFN Torino (IT))
• Simon Akar (University of Cincinnati (US))

Workshop: Identification, reconstruction, and experimental design

• Lorenzo Moneta (CERN)
• Pietro Vischia (Universite Catholique de Louvain (UCL) (BE))

28. Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders

Breno Orzari (UNESP - Universidade Estadual Paulista (BR))

10/05/2022, 16:05

Short talk

At the LHC, the full-simulation workflow requires a large fraction of the computing resources available for experiments. With the planned High Luminosity upgrade of the LHC, the amount of needed simulated datasets would even increase. Speeding up the simulation workflow is of crucial importance for the success of the HL-LHC program and Deep Learning is considered as a promising approach to...

43. Hadrons, Better, Faster, Stronger

Engin Eren

10/05/2022, 16:20

Regular talk

Precise modeling of physical processes is a crucial part of modern particle physics. However simulation of particle showers within a calorimeter requires significant computational resources. Fast and exact machine-learning-based shower simulators offer a promising way of alleviate this problem.

This work reports progress on two important fronts. First, the WGAN and BIB-AE generative models,...

27. SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics.

Mr Atul Kumar Sinha (University of Geneva)

10/05/2022, 16:45

Regular talk

Deep learning methods have gained popularity in high energy physics for fast modeling of particle showers in detectors. Detailed simulation frameworks such as the gold standard GEANT4 are computationally intensive, and current deep generative architectures work on discretized, lower resolution versions of the detailed simulation.
The development of models that work at higher spatial...

15. Calibrating stochastic simulations with optimal transport

Philipp Windischhofer (University of Oxford (GB))

10/05/2022, 17:10

Regular talk

Stochastic simulators are an indispensable tool in many branches of science. Often based on first principles, they deliver a series of samples whose distribution implicitly defines a probability measure to describe the phenomena of interest. However, the fidelity of these simulators is not always sufficient for all scientific purposes, necessitating the construction of ad-hoc corrections to...

52. Conditional Invertible Network for Neutrino Regression

Mr Matthew Leigh (University of Geneva)

11/05/2022, 09:00

Regular talk

The mass of the top quark is of paramount importance as it is a highly sensitive probe of the structure and stability of the Standard Model. The final state of a leptonically decaying top quark contains a neutrino. In collider physics the neutrino escapes detection, leaving only experimental proxies for its momentum in the plane transverse to the beam pipe and no information about its...

47. Uncertainty Aware Learning for High Energy Physics With A Cautionary Tale

Aishik Ghosh (University of California Irvine (US))

11/05/2022, 09:25

Lightning talk

Machine learning tools provide a significant improvement in sensitivity over traditional analyses by exploiting subtle patterns in high-dimensional feature spaces. These subtle patterns may not be well-modeled by the simulations used for training machine learning methods, resulting in an enhanced sensitivity to systematic uncertainties. Contrary to the traditional wisdom of constructing an...

4. Learning New Physics aware of systematic uncertainties

Gaia Grosso (Universita e INFN, Padova (IT))

11/05/2022, 09:30

Short talk

New Physics Learning Machine (NPLM) is a novel machine-learning based strategy to detect multivariate data departures from the Standard Model predictions, with no prior bias on the nature of the new physics responsible for the discrepancy [[1][1], [2][2]]. The main idea behind the method is to build the log-likelihood-ratio hypothesis test by translating the problem of maximizing the...

35. Learning Optimal Test Statistics in the Presence of Nuisance Parameters

Lukas Alexander Heinrich (CERN)

11/05/2022, 09:45

Short talk

The design of optimal test statistics is a key task in frequentist statistics and for a number of scenarios optimal test statistics such as the profile-likelihood ratio are known. By turning this argument around we can find the profile likelihood ratio even in likelihood-free cases, where only samples from a simulator are available, by optimizing a test statistic within those scenarios. We...

58. Spatio-Temporal Anomaly Detection for the DQM of the CMS Experiment via Graph Networks

Mulugeta Asres (University of Agder (NO))

11/05/2022, 10:00

Regular talk

The Data Quality Monitoring (DQM) is in place to spot and diagnose particle physics data problems as promptly as possible to avoid data loss in the CMS experiment of CERN. Several studies have proposed to leverage the DQM automation using machine learning algorithms. However, only a few efforts explored temporal characteristics to underpin system monitoring automation of the CMS detectors via...

3. Truncated Marginal Neural Ratio Estimation with swyft

Benjamin Kurt Miller (University of Amsterdam)

11/05/2022, 15:00

Regular talk

Parametric stochastic simulators are ubiquitous in science, often featuring high-dimensional input parameters and/or an intractable likelihood. Performing Bayesian parameter inference in this context can be challenging. We present a neural simulation-based inference algorithm which simultaneously offers simulation efficiency and fast empirical posterior testability, which is unique among...

32. Summary of Learning To Discover workshop

David Rousseau (IJCLab-Orsay)

11/05/2022, 15:25

Regular talk

Learning To Discover event has taken place 19th to 29th April 2022.
Three themes have been selected based on the one hand, their interest for HEP, and the fact there is already a number of HEP teams working on it, on the other hand, their importance in the Machine Learning field : Representation Learning over Heterogeneous/Graph Data, Dealing with Uncertainties and Generative Models. A final...

53. Autoencoders for semivisible jet detection

Jeremi Niedziela (ETH Zurich (CH))

11/05/2022, 15:50

Lightning talk

The production of dark matter particles from confining dark sectors may lead to many novel experimental signatures. Depending on the details of the theory, dark quark production in proton-proton collisions could result in semivisible jets of particles: collimated sprays of dark hadrons of which only some are detectable by particle collider experiments. The experimental signature is...

34. Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging

Taoli Cheng (University of Montreal)

11/05/2022, 15:55

Lightning talk

We leverage representation learning and the inductive bias in neural-net-based Standard Model jet classification tasks, to detect non-QCD signal jets. In establishing the framework for classification-based anomaly detection in jet physics, we demonstrate that with a \emph{well-calibrated} and \emph{powerful enough feature extractor}, a well-trained \emph{mass-decorrelated} supervised Standard...

14. Cosmological Simulation-Based Inference with Truncated Marginal Neural Ratio Estimation

Alex Cole

11/05/2022, 16:30

Regular talk

I will describe some applications of Truncated Marginal Neural Ratio Estimation (TMNRE) to cosmological simulation-based inference. In particular, I will report on using SBI for CMB power spectra (based on https://arxiv.org/abs/2111.08030) and realistic 21cm simulations (work in progress). Along the way, I plan to discuss some thoughts on how to incorporate active learning scenarios with...

6. CURTAINs for you Sliding Window: Constructing Unobserved Regions by Transporting Adjacent INtervals to improve the reach of bump hunts in the search for new physics

Debajyoti Sengupta (Universite de Geneve (CH))

11/05/2022, 16:55

Regular talk

In this talk we present CURTAINs, a new data driven ML technique for constructing a background template on a resonant spectrum, for use in bump hunts in the search for new physics using a sliding window approach. By employing invertible neural networks to parametrise the distribution of side band data as a function of the resonant observable, we learn a transformation to map any data point...

55. Object condensation for end-to-end reconstruction in high occupancy calorimeters with graph neural networks

Shah Rukh Qasim (Manchester Metropolitan University (GB))

11/05/2022, 17:20

Regular talk

We present an end-to-end reconstruction algorithm to build particle candidates from detector hits in next-generation granular calorimeters similar to that foreseen for the high-luminosity upgrade of the CMS detector. The algorithm exploits a distance-weighted graph neural network [2], trained with object condensation [1], a graph segmentation technique. Through a single-shot approach, the...

49. Anomaly detection for the quality control of silicon sensor wafers for the CMS HGCAL upgrade

Sonja Grönroos (University of Helsinki (FI))

11/05/2022, 17:45

Short talk

With the approaching HL-LHC upgrade, the current endcap calorimeters of the CMS are to be replaced with the High Granularity Calorimeter (HGCAL). Most of the sensitive part of HGCAL will consist of approximately 25,000 silicon pad sensor wafers, each approximately 20 cm in diameter, covering a total area of more than 600 m${}^2$ of silicon sensors. Electrical breakdowns have been observed during...

5. Clustering for interpreting complex high-energy physics models

Walter Hopkins (Argonne National Laboratory (US))

11/05/2022, 18:00

Lightning talk

After discovering the last piece of the Standard Model (SM), the Higgs boson, experiments at the Large Hadron Collider (LHC) have been searching for hints of physics Beyond the SM (BSM) to yield insights into these phenomena. These searches have not yet produced any significant deviations from SM predictions. Identifying unexplored regions in experimental observable space (object pTs, MET,...

33. Calomplification: The Power of Generative Calorimeter Models

Sebastian Guido Bieringer (Hamburg University)

12/05/2022, 09:00

Regular talk

Motivated by the high computational costs of classical simulations, machine-learned generative models can be extremely useful in particle physics and elsewhere. They become especially attractive when surrogate models can efficiently learn the underlying distribution, such that a generated sample outperforms a training sample of limited size. This kind of GANplification has been observed for...

56. How to generate all possible simulations with GANs?

Jan Michal Dubinski (Warsaw University of Technology (PL))

12/05/2022, 09:25

Lightning talk

The development of faster simulation methods is one of the crucial tasks currently undertaken at CERN. A part of this process in the ALICE experiment is the deep learning-based simulation tool for the Zero Degree Calorimeters (ZDC).

Generative models such as GANs that are currently used in the fast simulation framework successfully replicate the results for input particles that produce...

13. Information-theoretic stochastic contrastive conditional GAN (InfoSCC-GAN) for physical data generation

Vitaliy Kinakh (Université de Genève (CH))

12/05/2022, 09:30

Regular talk

Cosmological simulations use generative deep learning models to generate galaxy images that are indiscernible from real images. Such simulations allow for a precise modeling of competing cosmological models as well as realistic propagation effects that affect observations. We present a new stochastic contrastive conditional generative adversarial network (InfoSCC-GAN) with explorable latent...

25. IEA-GAN: Intra-Event Aware GAN for the Fast Simulation of PXD Background at Belle II

Hosein Hashemi (LMU Munich)

12/05/2022, 09:55

Short talk

A realistic detector simulation is extremely important in particle physics. However, the current methods are very inefficient computationally since large amounts of resources are required for the readout, storage and distribution of simulation data. Deep generative models allow for more effective fast simulation of this information. Nevertheless, generating detector responses is a highly...

1. An infra-red and collinear safe message passing neural network

Mr Vishal Singh Ngairangbam

12/05/2022, 10:35

Regular talk

Hadronic signals of new-physics origin at the Large Hadron Collider can remain hidden within the copiously produced hadronic jets. Unveiling such signatures require highly performant deep-learning algorithms. We construct a class of Graph Neural Networks (GNN) in the message-passing formalism that makes the network output infra-red and collinear (IRC) safe, an important criterion satisfied...

38. Quarks and gluons in the Lund plane

Adam Takacs (University of Bergen), Dr Frederic Alexandre Dreyer (University of Oxford), Gregory Soyez (IPhT, CEA Saclay)

12/05/2022, 11:00

Short talk

Discriminating quark and gluon jets is a long-standing topic in collider phenomenology. In this paper, we address this question using the Lund jet plane substructure technique introduced in recent years. We present two complementary approaches: one where the quark/gluon likelihood ratio is computed analytically, to single-logarithmic accuracy, in perturbative QCD, and one where the Lund...

31. Targeting Multi-Loop Integrals with Neural Networks

Ramon Winterhalder (UC Louvain)

12/05/2022, 11:15

Regular talk

Numerical evaluations of Feynman integrals often proceed via a deformation of the integration contour into the complex plane. While valid contours are easy to construct, the numerical precision for a multi-loop integral can depend critically on the chosen contour. We present methods to optimize this contour using a combination of optimized, global complex shifts and a normalizing flow. They...

40. Towards a Deep Learning Model for Hadronization

Andrzej Konrad Siodmok (Jagiellonian University (PL))

12/05/2022, 11:40

Regular talk

Hadronization is a complex quantum process whereby quarks and gluons become hadrons. The widely-used models of hadronization in event generators are based on physically-inspired phenomenological models with many free parameters. We propose an alternative approach whereby neural networks are used instead. Deep generative models are highly flexible, differentiable, and compatible with Graphical...

30. Using Machine Learning techniques in phenomenological studies in flavour physics

Jorge Alda Gallo (Universidad de Zaragoza)

12/05/2022, 12:05

Lightning talk

In the recent years, a series of measurements in the observables $R_{K^{(\ast )}}$ and $R_{D^{(\ast )}}$ concerning the semileptonic decays of the $B$ mesons have shown hints of violations of Lepton Flavour Universality (LFU). An updated model-independent analysis of New Physics violating LFU, by using the Standard Model Effective Field Theory (SMEFT) Lagrangian with semileptonic dimension six...

9. Turbo-Sim: a generalised generative model with a physical latent space

Guillaume Quétant (Université de Genève (CH))

12/05/2022, 13:30

Regular talk

We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model. By maximising the mutual information between the input and the output of both the encoder and the decoder, we are able to rediscover the loss terms usually found in adversarial autoencoders and generative adversarial networks, as well as various more...

18. Funnels: Exact maximum likelihood with dimensionality reduction

Samuel Byrne Klein (Universite de Geneve (CH))

12/05/2022, 13:55

Regular talk

Normalizing flows are exact likelihood models that have been useful in several applications in HEP. The use of these models is hampered by the dimension preserving nature of the transformations, which results in many parameters and makes the models unusable for some techniques. In this talk we introduce [funnels][1], a new family of dimension reducing exact likelihood models.

Funnel models...

16. ML-based Correction to Accelerate Geant4 Calorimeter Simulations

Evangelos Kourlitis (Argonne National Laboratory (US))

12/05/2022, 14:20

Lightning talk

The Geant4 detector simulation, using full particle tracking (FullSim), is usually the most accurate detector simulation used in HEP but it is computationally expensive. The cost of FullSim is amplified in highly segmented calorimeters where large fraction of the computations are performed to track the shower’s low-energy photons through the complex geometry. A method to limit the amount of...

51. Particle identification with machine learning in ALICE Run 3

Maja Kabus (Warsaw University of Technology (PL))

12/05/2022, 14:25

Regular talk

Particle identification (PID) is an essential ingredient of many measurements performed by the ALICE Collaboration. The ALICE detectors provide PID information via complementary experimental techniques, allowing for the identification of particles over a broad momentum interval ranging from about 100 MeV/c up to 20 GeV/c. The biggest challenge lies in combining the information from the...

57. Data-driven machine learning algorithms for the calibration of space-charge distortion fluctuations in the ALICE TPC

Marian Ivanov (GSI - Helmholtzzentrum fur Schwerionenforschung GmbH (DE))

12/05/2022, 14:50

Short talk

The Time Projection Chamber (TPC) of the ALICE experiment at CERN LHC was upgraded for Run 3 and Run 4. Readout chambers based on Gas Electron Multiplier (GEM) technology and a new readout scheme allow continuous data acquisition at the highest interaction rates expected in Pb-Pb collisions. In the absence of a gating grid system, a significant amount of ions generated in the multiplication...

45. FPGA acceleration of the CMS DNN based LLP Jet Algorithm for the LHC High-Luminosity upgrade

Tarik Ourida

12/05/2022, 15:40

Regular talk

The CMS experiment at the Large Hadron Collider (LHC) at CERN adopts the LLP (Long-Lived Particle) Jet Algorithm, to search for new physics by tagging hadronic jets which stem from exotic long-lived particles. The LLP Jet Algorithm is a multiclass classifier based on a state-of-the-art Deep Neural Network (DNN). The jet tagging model’s forward inference stage employs 12 convolutional layers...

41. Ephemeral Learning - Augmenting Triggers with Online-Trained Normalizing Flows

Sascha Daniel Diefenbacher (Hamburg University (DE))

12/05/2022, 16:05

Short talk

The large data rates at the LHC make it impossible to store every single observed interaction. Therefore we require an online trigger system to select relevant collisions. We propose an additional approach, where rather than compressing individual events, we compress the entire data set at once. We use a normalizing flow as a deep generative model to learn the probability density of the data...

21. Optimized Deep Learning Inference on High Level Trigger at the LHC: Computing time and Resource assessment

Syed Anwar Ul Hasan (Universita & INFN Pisa (IT))

12/05/2022, 16:20

Short talk

We present a study on latency and resource requirements for deep learning algorithms to run on a typical High Level Trigger computing farm at a high-pT LHC experiment at CERN. As a benchmark, we consider convolutional and graph autoencoders, developed to perform real-time anomaly detection on all the events entering the High Level Trigger (HLT) stage. The benchmark dataset consists of...

20. Unsupervised learning for real-time SUEP detection in a High Level Trigger system at the LHC

Simranjit Singh Chhibra (CERN)

12/05/2022, 16:35

Lightning talk

We propose a signal-agnostic strategy to reject QCD jets and identify anomalous signatures in a High Level Trigger (HLT) system at the LHC. Soft unclustered energy patterns (SUEP) could be such a signal — predicted in models with strongly-coupled hidden valleys — primarily characterized by a nearly spherically-symmetric signature of an anomalously large number of soft charged particles, in...

10. Neural network based primary vertex reconstruction with FPGAs for the upgrade of the CMS level-1 trigger system

Matthias Komm (Deutsches Elektronen-Synchrotron (DE))

12/05/2022, 16:40

Short talk

The CMS experiment will be upgraded to maintain physics sensitivity and exploit the higher luminosity of the High Luminosity LHC. Part of this upgrade will see the first level (Level-1) trigger use charged particle tracks within the full outer silicon tracker volume as an input for the first time and new algorithms are being designed to make use of these tracks. One such algorithm is primary...

8. Multi-objective optimization for the CMS High Granularity Calorimeter Level 1 trigger

Alexandre Hakimi (Centre National de la Recherche Scientifique (FR))

12/05/2022, 16:55

Lightning talk

The CMS collaboration has chosen a novel High-Granularity Calorimeter (HGCAL) for the endcap regions as part of its planned upgrade for the high luminosity LHC. The high granularity of the detector is crucial for disentangling showers overlapped with high levels of pileup events (140 or more per bunch crossing at HL-LHC). But the reconstruction of the complex events and rejection of background...

17. Neural network distributed training and optimization library (NNLO)

Irena Veljanovic (CERN)

13/05/2022, 09:00

Regular talk

With deep learning becoming very popular among LHC experiments, it is expected that speeding up the network training and optimization will soon be an issue. To this purpose, we are developing a dedicated tool at CMS, Neural Network Learning and Optimization library (NNLO). NNLO aims to support both widely known deep learning libraries Tensorflow and PyTorch. It should help engineers and...

12. MLaaS4HEP: Machine Learning as a Service for HEP

Luca Giommi (Universita e INFN, Bologna (IT))

13/05/2022, 09:25

Lightning talk

Nowadays Machine Learning (ML) techniques are widely adopted in many areas of HEP and certainly will play a significant role also in the upcoming High-Luminosity LHC (HL-LHC) upgrade foreseen at CERN, when a huge amount of data will be produced by LHC and collected by the experiments, facing challenges at the exascale.

Here, we present a Machine Learning as a Service solution for HEP...

19. Quantum Machine Learning algorithms in the latent space of HEP events

Kinga Anna Wozniak (University of Vienna (AT))

13/05/2022, 09:30

Regular talk

We present a study, based on supervised and unsupervised quantum machine learning algorithms, with the goal of proposing a new strategy for anomaly detection at the LHC. This study focuses on designing an algorithm capable of finding hidden patterns in the jet data. The algorithm is structured as a sequence of a classic and a quantum machine learning algorithm: the classic algorithm is the...

7. GNN-based algorithm for full-event filtering and interpretation at the LHCb trigger

Julian Garcia Pardinas (Universita & INFN, Milano-Bicocca (IT))

13/05/2022, 09:55

Regular talk

The LHCb experiment is currently undergoing its Upgrade I, which will allow it to collect data at a five-times larger instantaneous luminosity. In a decade from now, the Upgrade II of LHCb will prepare the experiment to face another ten-fold increase in instantaneous luminosity. Such an increase in event complexity will pose unprecedented challenges to the online-trigger system, for which a...

36. Graph Neural Network Track Reconstruction for the ATLAS ITk Detector

Daniel Thomas Murnane (Lawrence Berkeley National Lab. (US))

13/05/2022, 10:20

Regular talk

Graph Neural Networks (GNNs) have been shown to produce high accuracy performance on a variety of HEP tasks, including track reconstruction in the TrackML challenge, and tagging in jet physics. However, GNNs are less explored in applications with noisy, heterogeneous or ambiguous data. These elements are expected from ATLAS Inner Tracker (ITk) detector data, when it is reformulated as a graph....

50. Application of artificial intelligence in the reconstruction of signals from the PADME electromagnetic calorimeter

Kalina Stoimenova (Sofia University "St. Kliment Ohridski")

13/05/2022, 11:15

Lightning talk

PADME experiment at LNF-INFN is devoted to the search for the associate production of new light particles using accelerated positrons which annihilate in a thin active diamond target.
The core of the experiment is an electromagnetic calorimeter made of 616 BGO crystals which is dedicated to the measurement of the energy and the position of the final state photons.
The high beam particle...

46. Semi-supervised Graph Neural Networks for Pileup Noise Removal

Garyfallia Paspalaki (Purdue University (US))

13/05/2022, 11:20

Lightning talk

The high instantaneous luminosity of the CERN Large Hadron Collider leads to multiple proton-proton interactions in the same or nearby bunch crossings (pileup). Advanced pileup mitigation algorithms are designed to remove this noise from pileup particles and improve the performance of crucial physics observables. This study implements a semi-supervised graph neural network for particle-level...

44. CBM performance for (multi-)strange hadron measurements using Machine Learning techniques

Shahid Khan

13/05/2022, 11:25

Lightning talk

The Compressed Baryonic Matter (CBM) experiment at FAIR will investigate the QCD phase diagram at high net-baryon density (${\mu }_B>400$ MeV) in the energy range of $\sqrt{s_{NN}}$ = 2.7−4.9 GeV. Precise determination of dense baryonic matter properties requires multi-differential measurements of strange hadron yields, both for most copiously produced kaons and $\mathrm{\Lambda }$ as well as for rare...

37. Leveraging universality of jet taggers through transfer learning

Radoslaw Piotr Grabarczyk

13/05/2022, 11:30

Regular talk

A significant challenge in the tagging of boosted objects via machine-learning technology is the prohibitive computational cost associated with training sophisticated models. Nevertheless, the universality of QCD suggests that a large amount of the information learnt in the training is common to different physical signals and experimental setups. In this article, we explore the use of transfer...

29. Particle Transformer for Jet Tagging

Sitian Qian (Peking University (CN))

13/05/2022, 11:55

Regular talk

Jet tagging is a critical yet challenging classification task in particle physics. While deep learning has transformed jet tagging and significantly improved performance, the lack of a large-scale public dataset impedes further enhancement. In this work, we present JetClass, a new comprehensive dataset for jet tagging. The JetClass dataset consists of 100 M jets, about two orders of magnitude...

26. ML for SUEP Detection

Luca Marco Lavezzo (MIT)

13/05/2022, 12:20

Lightning talk

We explore a possible avenue for detecting Dark Showers that manifest as Soft Unclustered Energy Patterns (SUEP) in the detector with the use of supervised machine learning techniques and transfer learning. We employ a ResNet model based on Convolutional Neural Networks (CNNs) to classify events. Additionally, a robust, data-driven background estimation technique is embedded into the model...

24. Using Graph autoencoders to trigger on new physics at the LHC

Muhammad-Hassan Shahid

13/05/2022, 12:25

Lightning talk

We investigate the potential of graph neural networks in unsupervised search for new physics signatures in the extremely challenging environment at the L1 at the Large Hadron Collider (LHC). On a dataset mimicking the hardware-level trigger input, we demonstrate that graph autoencoders can significantly enhance new physics contributions. Moreover, we implement the graph autoencoder on FPGA to...

23. Likelihood-Free Frequentist Inference for Calorimetric Muon Energy Measurement

Luca Masserano (Carnegie Mellon University)

13/05/2022, 14:00

Regular talk

Calorimetric muon energy estimation in high-energy physics is an example of a likelihood-free inference (LFI) problem, where simulators that implicitly encode the likelihood function are used to mimic complex interactions at different configurations of the parameters. Recently, Kieseler et al. (2022) exploited simulated measurements from a dense, finely segmented calorimeter to infer the true...

42. Two-level graphs for muon-tomography inference

Dr Giles Chatham Strong (Universita e INFN, Padova (IT))

13/05/2022, 14:25

Regular talk

Muon tomography is a useful imaging technique for studying volumes of interest by examining the scattering and absorption of cosmic muons which pass through them. Inferring properties of the volumes, however, is challenging since muons will scatter many times within the volume, the detectors involved have finite resolution, and each muon only ever traverses a sub-potion of the whole...

22. Electron identification in ATLAS using a deep neural network

Lukas Ehrke (Universite de Geneve (CH))

13/05/2022, 14:50

Lightning talk

The currently used identification of electrons in ATLAS uses a likelihood approach without considering correlations between the input variables. In this talk we introduce the next generation identification algorithm using the same input information but with a deep neural network in order to extract more information from the input variables and substantially improve the rejection of fake...

11. Tracking of Proton Traces in a Digital Tracking Calorimeter using Reinforcement Learning

Tobias Kortus (University of Applied Sciences Worms)

13/05/2022, 14:55

Short talk

Particle therapy using protons or heavy ions is a relatively new cancer treatment modality which has acquired increasing popularity in the last decade, due to its potential in reducing undesired dose to the nearby healthy tissues, with respect to conventional radiotherapy. However, current clinical treatment planning based on computed tomography suffers from modest range uncertainties due to...

48. Point Cloud Deep Learning Methods for Pion Reconstruction in the ATLAS Detector

Mariel Pettee (Lawrence Berkeley National Lab. (US))

13/05/2022, 15:10

Regular talk

Reconstructing the type and energy of isolated pions from the ATLAS calorimeters is a key step in the hadronic reconstruction. The baseline methods for local hadronic calibration were optimized early in the lifetime of the ATLAS experiment. Recently, image-based deep learning techniques demonstrated significant improvements over the performance over these traditional techniques. We present an...

39. Explaining machine-learned particle-flow reconstruction

Farouk Mokhtar (Univ. of California San Diego (US))

13/05/2022, 15:35

Regular talk

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. A graph neural network (GNN) model, known as the machine-learned particle-flow (MLPF) algorithm, has been developed to substitute the rule-based PF algorithm (https://arxiv.org/abs/2101.08578),...

2. Anomaly detection with SOFIE

Juan Antonio Aguilar Saavedra (Consejo Superior de Investigaciones Cientificas (CSIC) (ES))

Lightning talk

I will discuss a new concept in anomaly detection based on (1) tagging of objects to detect "exotic" ones (2) search for anomalous features by comparing the untagged and tagged samples. Both (1) and (2) are done with ML tools, either supervised or non-supervised. In the current implementation for multi-pronged jets, tagging is supervised and the search for features is unsupervised.

54. Measuring a New Class of Jet Observables with Neural Network Based Unfolding

Jingjing Pan (Yale University (US))

Regular talk

Jets are collimated sprays of hadrons produced in high energy collisions. Jets play an important role in many searches for new physics, and provide an experimental window into the real time dynamics of hadronization, namely the confinement of asymptotically free quarks and gluons into hadrons. With the advent of a new class of theoretical observables, so called energy correlators, that probe...