ML4Jets2023

Contribution List

133. Welcome and Logistics

06/11/2023, 09:15

Opening

134. Experimental Introducton

Kevin Pedro (Fermi National Accelerator Lab. (US))

06/11/2023, 09:30

Opening

135. Modern Machine Learning for the LHC Simulation Chain

Ramon Winterhalder (UCLouvain)

06/11/2023, 10:00

Opening

50. Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows

Thorsten Buss (Universität Hamburg (DE))

06/11/2023, 11:00

Generative Models and Simulation

The full simulation of particle colliders incurs a significant computational cost. Among the most resource-intensive steps are detector simulations. It is expected that future developments, such as higher collider luminosities and highly granular calorimeters, will increase the computational resource requirement for simulation beyond availability. One possible solution is generative neural...

77. Reconstructing and calibrating hadronic objects with ML/AI algorithms in ATLAS

Tobias Fitschen (University of Manchester (GB))

06/11/2023, 11:00

Tagging Techniques

Experimental uncertainties related to the calibration of hadronic objects (particularly the jet energy scale and resolution) can limit the precision of physics analyses at the LHC, and so improvements in performance have the potential to broadly increase the impact of results. Such settings are among most promising for cutting-edge machine learning and artificial intelligence algorithms at the...

55. Boosted Jet Tagging and Calibration in CMS

Oz Amram (Fermi National Accelerator Lab. (US))

06/11/2023, 11:15

Tagging Techniques

This talk will overview the usage of boosted multi-prong jet tagging in CMS and how such taggers are calibrated. It will highlight a new method for calibrating the tagging of multi-prong jets using the Lund Jet Plane to correct the substructure of simulated jets. The method is shown to significantly improve the data-simulation agreement of substructure observables.

123. Pushing Normalizing Flows for higher-dimensional Detector Simulations

Florian Ernst

06/11/2023, 11:15

Generative Models and Simulation

Normalizing-flow architectures have shown outstanding performance in various generative tasks at the LHC. However, they don't scale well to higher dimensional datasets. We investigate several directions to improve normalizing flows for calorimeter shower simulations: 1) using a coupling-layer based flow to improve training and generation times without dimensionality reduction, and 2), using a...

3. Attention to Mean Fields for Particle Cloud Generation

Benno Kach (Deutsches Elektronen-Synchrotron (DE))

06/11/2023, 11:30

Generative Models and Simulation

The use of machine learning for collider data generation has become a significant area of study within particle physics. This interest arises from the increasing computational difficulties associated with traditional Monte Carlo simulation methods, especially in the context of future high-luminosity colliders. Representing collider data as particle clouds introduces several advantageous...

85. Vertex Reconstruction with Transformers

Nikita Ivvan Pond (University of London (GB))

06/11/2023, 11:30

Tagging Techniques

The identification of heavy-flavour jets (tagging) remains a critical task at hadron colliders. A key signature of such jets is the displaced decay vertices left by boosted b- and c-hadrons. While existing tagging algorithms leveraged manually designed algorithms to identify and fit vertices, they were succeeded by edge-classification based Graph Neural Networks (GNNs) that, despite...

73. Latent Generative Models for Fast Calorimeter Simulation

Qibin Liu (Tsung-Dao Lee Institute (CN) & Shanghai Jiao Tong University (CN))

06/11/2023, 11:45

Generative Models and Simulation

Simulation of calorimeter response is a crucial part of detector study for modern high energy. The computational cost of conventional MC-based simulation becoming a major bottleneck with the increasingly large and high granularity design. We propose a 2-step generative model for fast calorimeter simulation based on Vector-Quantized Variational Autoencoder (VQ-VAE). This model achieves a fast...

61. Performance of heavy flavour jet identification in boosted topologies in CMS 13 TeV data

Matteo Marchegiani (ETH Zurich (CH))

06/11/2023, 11:45

Tagging Techniques

Physics measurements in the highly Lorentz-boosted regime, including the search for the Higgs boson or beyond standard model particles, are a critical part of the LHC physics program. In the CMS Collaboration, various boosted-jet tagging algorithms, designed to identify hadronic jets originating from a massive particle decaying to bb̅ or cc̅, have been developed and deployed in a variety of...

119. New Angles on Fast Calorimeter Shower Simulation

Peter McKeown

06/11/2023, 12:00

Generative Models and Simulation

The simulation requirements of experiments in high energy physics place major demands on the available computing resources. These simulation pressures are projected to increase further at the upcoming high luminosity phase of the LHC and for future colliders. An additional challenge arises from the significantly higher granularity present in future detectors, which increases the physical...

114. Towards Novel Charged Particle Tracking Approaches with Transformer and U-Net Models

Zef Wolffs (Nikhef National institute for subatomic physics (NL))

06/11/2023, 12:00

Tagging Techniques

Inspired by the recent successes of language modelling and computer vision machine learning techniques, we study the feasibility of repurposing these developments for particle track reconstruction in the context of high energy physics. In particular, drawing from developments in the field of language modelling we showcase the performance of multiple implementations of the transformer model,...

28. Improved selective background Monte Carlo simulation at Belle II with graph attention networks and weighted events

Boyang Yu

06/11/2023, 12:15

Generative Models and Simulation

When measuring rare processes at Belle II, a huge luminosity is required, which means a large number of simulations are necessary to determine signal efficiencies and background contributions. However, this process demands high computation costs while most of the simulated data, in particular in case of background, are discarded by the event selection. Thus, filters using graph neural networks...

121. Event Reconstruction with GNNs at the FCC

Dolores Garcia (CERN)

06/11/2023, 14:00

Reconstruction

The FCC will deliver a large dataset thanks to its unprecedented luminosity. Improving the quality of the event reconstruction at different levels will allow to increase the accuracy of the physics measurements we can achieve. For example, at the particle-level reconstruction, where information from different sub-detectors e.g tracker and calorimeter is available, ML shows promise to improve...

59. Regression-based refinement of fast simulation

Moritz Jonas Wolf (Hamburg University (DE))

06/11/2023, 14:00

Super Resolution, Reweighting, and Refinement

At experiments at the LHC, a growing reliance on fast Monte Carlo applications will accompany the high luminosity and detector upgrades of the Phase 2 era. Traditional FastSim applications which have already been developed over the last decade or more may help to cope with these challenges, as they can achieve orders of magnitude greater speed than standard full simulation applications....

26. Refining Fast Calorimeter Simulations with a Schrödinger Bridge

Sascha Diefenbacher (Lawrence Berkeley National Lab. (US))

06/11/2023, 14:15

Super Resolution, Reweighting, and Refinement

Machine learning-based simulations, especially calorimeter simulations, are promising tools for approximating the precision of classical high energy physics simulations with a fraction of the generation time. Nearly all methods proposed so far learn neural networks that map a random variable with a known probability density, like a Gaussian, to realistic-looking events. In many cases, physics...

115. Time-of-Flight Estimation using Machine Learning Techniques

Konrad Helms

06/11/2023, 14:15

Reconstruction

Time-of-flight (TOF) reconstruction is under investigation as a method to enhance the particle identification capabilities of detectors proposed for future Higgs factories. By utilising time measurements based on energy deposits of showers in the calorimeter system, the TOF of the particle can be inferred. The focus of our studies is the International Large Detector (ILD), a proposed detector...

56. Set2Tree: Particle decay reconstruction via GNN

Dmitrii Kobylianskii (Weizmann Institute of Science (IL))

06/11/2023, 14:30

Reconstruction

Tree structure is a natural way to represent particle decays in high energy physics. The possibility of reconstructing the entire decay tree that ends in stable particles entering the detector is an interesting and potentially beneficial task. [The interesting and extremely helpful task is to reconstruct the entire decay process, starting from the leaf nodes, which are the reconstructed...

80. SuperCalo: Calorimeter shower super-resolution

Ian Pang

06/11/2023, 14:30

Super Resolution, Reweighting, and Refinement

Calorimeter shower simulation is a major bottleneck in the Large Hadron Collider computational pipeline. There have been recent efforts to employ deep-generative surrogate models to overcome this challenge. However, many of best performing models have training and generation times that do not scale well to high-dimensional calorimeter showers. We introduce SuperCalo, a flow-based...

51. Denoising Graph Super-Resolution with Diffusion Models and Transformers for Improved Particle Reconstruction

Nilotpal Kakati (Weizmann Institute of Science (IL))

06/11/2023, 14:45

Super Resolution, Reweighting, and Refinement

Accurately reconstructing particles from detector data is a critical challenge in experimental particle physics. The detector's spatial resolution, specifically the calorimeter's granularity, plays a crucial role in determining the quality of the particle reconstruction. It also sets the upper limit for the algorithm's theoretical capabilities. Super-resolution techniques can be explored as a...

48. End-to-end analysis with jointly optimized particle identification and analysis optimization objectives

Matthias Vigl (Technische Universitat Munchen (DE))

06/11/2023, 14:45

Reconstruction

Most searches at the LHC employ an analysis pipeline consisting of various discrete components, each individually optimized and later combined to provide relevant features used to discriminate SM background from potential signal. These are typically high-level features constructed from particle four-momenta. However, the combination of individually optimized tasks doesn't guarantee an optimal...

25. SR-GAN for SR-gamma: photon super resolution at collider experiments

Florian Alexander Mausolf (Rheinisch Westfaelische Tech. Hoch. (DE))

06/11/2023, 15:00

Super Resolution, Reweighting, and Refinement

Photons are important objects at collider experiments. For example, the
Higgs boson is studied with high precision in the diphoton decay channel. For this purpose, it is crucial to achieve the best possible spatial resolution for photons and to discriminate against other particles which mimic the photon signature, mostly Lorentz-boosted $\pi^0\to\gamma\gamma$ decays.

In this talk, a study...

21. ν²-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows

Johnny Raine (Universite de Geneve (CH)), Mr Matthew Leigh (University of Geneva)

06/11/2023, 15:00

Reconstruction

In this work we introduce ν²-Flows, an extension of the ν-Flows method to final states containing multiple neutrinos. The architecture can natively scale for all combinations of object types and multiplicities in the final state for any desired neutrino multiplicities. In ttbar dilepton events, the momenta of both neutrinos and correlations between them are reconstructed more accurately than...

19. Reconstructing ALP properties and optimizing experimental design with simulation-based inference

Alessandro Morandini

06/11/2023, 15:15

Reconstruction

Axion-like particles (ALPs) arise in beyond the Standard Model theories with global symmetry breaking. Several experiments have been constructed and proposed to look for them at different energy scales. We focus here on beam-dump experiments looking for GeV scale ALPs with macroscopic decay lengths. In this work we show that using ML we can reconstruct the ALP properties (mass and lifetime)...

71. Generic representations of jets at detector-level with self supervised learning

Etienne Dreyer (Weizmann Institute of Science (IL))

06/11/2023, 16:00

Reconstruction & Representation Learning

Supervised learning has been used successfully for jet classification and to predict a range of jet properties, such as mass and energy. Each model learns to encode jet features, resulting in a representation that is tailored to its specific task. But could the common elements underlying such tasks be combined in a single model trained to extract features generically? To address this question,...

107. CoCo: Contrastive Combinatorics

Debajyoti Sengupta (Universite de Geneve (CH))

06/11/2023, 16:15

Reconstruction & Representation Learning

We present CoCo (Contrastive Combinatorics) a new approach using contrastive learning to solve object assignment in HEP. By utilizing contrastive objectives, CoCo aims to pull jets originating from the same parent closer together in an embedding space while pushing unrelated jets apart.
This approach can be extended natively to have multiple objectives for each subsequent particle in a decay...

122. Identifying semi-visible jets with darkCLR

Tanmoy Modak

06/11/2023, 16:30

Reconstruction & Representation Learning

Abstract: Unsupervised machine learning enables us to utilize all available information within a jet to identify anomalies. Nevertheless, the network's need to acquire knowledge about the inherent symmetries within the raw data structure can hinder this process. Self-supervised contrastive learning representation offers a novel approach that preserves physical symmetries in the data while...

62. Reconstructing full pp collision events with HGPflow

Nilotpal Kakati (Weizmann Institute of Science (IL))

06/11/2023, 16:45

Reconstruction & Representation Learning

Last year we proposed a novel hypergraph-based algorithm (HGPflow) for one-shot prediction of particle cardinality, class, and kinematics in a dataset of single jets. This approach has the advantage of introducing energy conservation as an inductive bias, promoting both interpretability and performance gains at the particle and jet levels. We now deploy an upgraded version of HGPflow to the...

89. Scalable neural network models and terascale datasets for particle-flow reconstruction

Joosep Pata (National Institute of Chemical Physics and Biophysics (EE))

06/11/2023, 17:30

Reconstruction & Representation Learning

We study scalable machine learning models for full event reconstruction in high-energy electron-positron collisions based on a highly granular detector simulation. Particle-flow (PF) reconstruction can be formulated as a supervised learning task using tracks and calorimeter clusters or hits. We compare a graph neural network and kernel-based transformer and demonstrate that both avoid...

23. Masked particle modelling

Mr Matthew Leigh (University of Geneva)

06/11/2023, 17:45

Reconstruction & Representation Learning

The Bert pretraining paradigm has proven to be highly effective in many domains including natural language processing, image processing and biology. To apply the Bert paradigm the data needs to be described as a set of tokens, and each token needs to be labelled. To date the Bert paradigm has not been explored in the context of HEP. The samples that form the data used in HEP can be described...

126. ML-assisted reconstruction of hadron-collider events with mini-jets

Josef Modestus Murnauer (Max Planck Society (DE))

06/11/2023, 18:00

Reconstruction & Representation Learning

The reconstruction of physical observables in hadron collider events from recorded experimental quantities poses a repeated task in almost any data analysis at the LHC. While the experiments record hits in tracking detectors and signals in the calorimeters, which are subsequently combined into particle-flow objects, jets, muons, electrons, missing transverse energy, or similar high-level...

43. Deep learning methods for noise filtering in the NA61/SHINE experiment

Marcin Slodkowski (Warsaw University of Technology (PL))

07/11/2023, 09:00

Low Latency and Elementary Inputs

The NA61/SHINE experiment is a prominent venture in high-energy physics, located at the SPS accelerator within CERN. Recently, the experiment's physics program underwent expansion, necessitating a comprehensive overhaul of its detector configuration. This upgrade is primarily geared towards augmenting the event flow rate, elevating it from 80Hz to 1kHz. This enhancement involves a substantial...

110. Learning a Representation of New Physics Models

Tore von Schwartz

07/11/2023, 09:00

Theory & Understanding

In the world of particle physics experiments, we often deal with data lying in high-dimensional spaces. Tasks like navigating and comparing these data points become challenging, but can be simplified with dimensionality reduction methods. In this work, we develop a method for mapping data originating from both Standard Model processes and various theories Beyond the Standard Model into a...

45. Anatomy of Jet classification using deep learning

Sung Hak Lim (Rutgers University)

07/11/2023, 09:15

Theory & Understanding

State-of-the-art (SoTA) deep learning models have achieved tremendous improvements in jet classification performance while analyzing low-level inputs, but their decision-making processes have become increasingly opaque. We introduce an analysis model (AM) that combines several phenomenologically motivated neural networks to circumvent the interpretability issue while maintaining high...

6. The application of neural networks for the calibration of topological cell clusters in the ATLAS calorimeters

Peter Loch (University of Arizona (US))

07/11/2023, 09:15

Low Latency and Elementary Inputs

The basic signal of the ATLAS calorimeters are three-dimensional clusters of topologically connected cell signals formed by following signal significance patterns. These topo-clusters provide measures of their shape, location and signal character which are employed to apply a local hadronic calibration. The corresponding multi-dimensional calibration functions are determined by training...

7. Hyperbolic Machine Learning for Jet Physics

Nathaniel Sherlock Woodward (Massachusetts Inst. of Technology (US))

07/11/2023, 09:30

Theory & Understanding

Particle jets exhibit tree-like structures through stochastic showering and hadronization. The hierarchical nature of these structures aligns naturally with hyperbolic space, a non-Euclidean geometry that captures hierarchy intrinsically. Drawing upon the foundations of geometric learning, we introduce hyperbolic transformer models tailored for tasks relevant to jet analyses, such as...

98. Jets as sets or graphs: Fast jet classification on FPGAs for efficient triggering at the HL-LHC

Denis-Patrick Odagiu (ETH Zurich (CH))

07/11/2023, 09:30

Low Latency and Elementary Inputs

The upcoming high-luminosity upgrade of the LHC will lead to a factor of five increase in instantaneous luminosity during proton-proton collisions. Consequently, the experiments situated around the collider ring, such as the CMS experiment, will record approximately ten times more data. Furthermore, the luminosity increase will result in significantly higher data complexity, thus making more...

88. A Convolutional Neural Network for topological fast selection algorithms in FPGAs for the HL-LHC upgrade of the CMS experimen

Maciej Mikolaj Glowacki (University of Bristol (GB))

07/11/2023, 09:45

Low Latency and Elementary Inputs

The High Luminosity upgrade to the LHC will deliver unprecedented luminosity to the experiments, culminating in up to 200 overlapping proton-proton collisions. In order to cope with this challenge several elements of the CMS detector are being completely redesigned and rebuilt. The Level-1 Trigger is one such element; it will have a 12.5 microsecond window in which to process protons colliding...

57. Realtime Anomaly Detection in the CMS Experiment Global Trigger Test Crate

Jannicke Pearkes (University of Colorado Boulder (US))

07/11/2023, 10:00

Low Latency and Elementary Inputs

We present the preparation, deployment, and testing of an autoencoder trained for unbiased detection of new physics signatures in the CMS experiment Global Trigger test crate FPGAs during LHC Run 3. The Global Trigger makes the final decision whether to readout or discard the data from each LHC collision, which occur at a rate of 40 MHz, within a 50 ns latency. The Neural Network makes a...

13. LLPNet: Graph Autoencoder for Triggering Light Long-Lived Particles at HL-LHC

Mr Prabhat Solanki (Indian Institute of Science, Bengaluru)

07/11/2023, 10:15

Low Latency and Elementary Inputs

In the search for exotic events involving displaced particles at HL-LHC, the triggering at the level-1 (L1) system will pose a significant challenge. This is particularly relevant in scenarios where low mass long-lived particles (LLPs) are coupled to a Standard Model (SM)-like 125 GeV Higgs boson and they decay into jets. The complexity arises from the low hadronic activity resulting from LLP...

105. Fitting a deep generative hadronization model

Adam Kania (Jagiellonian University)

07/11/2023, 11:00

Generative: Sets and Point Clouds

Based on: JHEP 09 (2023) 084:
Hadronization is a critical step in the simulation of high-energy particle and nuclear physics experiments. As there is no first principles understanding of this process, physically-inspired hadronization models have a large number of parameters that are fit to data. Deep generative models are a natural replacement for classical techniques, since they are more...

35. Fast Particle Cloud Generation with Flow Matching and Diffusion

Cedric Ewen

07/11/2023, 11:15

Generative: Sets and Point Clouds

We introduce two novel techniques for the efficient generation of jets as low-level particle clouds. Firstly, we present EPiC-JeDi, which integrates the score-based diffusion model from PC-JeDI with the fast and computationally efficient equivariant point cloud (EPiC) layers used in the EPiC-GAN. Secondly, we introduce EPiC-FM, which shares the same architecture but employs a continuous...

32. Beyond Kinematics: Generating Jets with Particle-ID and Trajectory Displacement Information

Joschka Valentin Maria Birk

07/11/2023, 11:30

Generative: Sets and Point Clouds

In this talk, we introduce a method for efficiently generating jets in the field of High Energy Physics.
Our model is designed to generate ten different types of jets, expanding the versatility of
jet generation techniques.
Beyond the kinematic features of the jet constituents, our model also excels in generating
informative features that provide insight into the types of jet constituents,...

31. CaloPointFlow - Generating Calorimeter Showers as Point Clouds

Simon Schnake (DESY / RWTH Aachen University)

07/11/2023, 11:45

Generative: Sets and Point Clouds

In particle physics, precise simulations of the interaction processes in calorimeters are essential for scientific discovery. However, accurate simulations using GEANT4 are computationally very expensive and pose a major challenge for the future of particle physics. In this study, we apply the CaloPointFlow model, a novel generative model based on normalizing flows, to fast and high-fidelity...

22. PC-Droid: Jet generation with diffusion

Debajyoti Sengupta (Universite de Geneve (CH))

07/11/2023, 12:00

Generative: Sets and Point Clouds

Building on the success of PC-JeDi we introduce PC-Droid, a substantially improved diffusion model for the generation of jet particle clouds. By leveraging a new diffusion formulation, studying more recent integration solvers, and training on all jet types simultaneously, we are able to achieve state-of-the-art performance for all types of jets across all evaluation metrics. We study the...

15. DeepTreeGAN: Fast Generation of High Dimensional Point Clouds

Mr Moritz Scham (Deutsches Elektronen-Synchrotron (DE))

07/11/2023, 12:15

Generative: Sets and Point Clouds

In High Energy Physics, detailed and time-consuming simulations are used for particle interactions with detectors. To bypass these simulations with a generative model, it needs to be able to generate large point clouds in a short time while correctly modeling complex dependencies between the particles.
For non-sparse problems on a regular grid, such a model would usually use (De-)Convolution...

18. Conditional Set-to-Set Generation for Fast Simulation using Diffusion and Graph-to-Graph Translation

Nathalie Soybelman (Weizmann Institute of Science (IL))

07/11/2023, 13:45

Generative: Diffusion Models

Simulating particle physics data is a crucial yet computationally expensive aspect of analyzing data at the LHC. Typically, in fast simulation methods, we rely on a surrogate calorimeter model to generate a set of reconstructed objects. This work demonstrates the potential to generate these reconstructed objects in a single step, effectively replacing both the calorimeter simulation and...

54. CaloGraph: Calorimeter simulation via Graph-based diffusion model

Dmitrii Kobylianskii (Weizmann Institute of Science (IL))

07/11/2023, 14:00

Generative: Diffusion Models

Calorimeter response simulation is a critical but computationally consuming part of many physics analyses at the Large Hadron Collider. The simulation time and resource consumption can be effectively reduced by the usage of neural networks. Denosing diffusion models are emerging as the state-of-the-art for various generative tasks ranging from images to sets. We propose a new graph-based...

87. Learning the language of QCD jets with transformers

Dr Alexander Mück (RWTH Aachen University)

07/11/2023, 14:00

Generative: Partons and Phase Space

Transformers have become the primary architecture for natural language processing. In this study, we explore their use for auto-regressive density estimation in high-energy jet physics. We draw an analogy between sentences and words in natural language and jets and their constituents. Specifically, we investigate density estimation for light QCD jets and hadronically decaying boosted top jets....

40. High-Dimensional Diffusion Generative Models in Collider Physics

Vinicius Massami Mikuni (Lawrence Berkeley National Lab. (US))

07/11/2023, 14:15

Generative: Diffusion Models

Diffusion generative models are a recent type of generative models that excel in various tasks, including those in collider physics and beyond. Thanks to their stable training and flexibility, these models can easily incorporate symmetries to better represent the data they generate. In this talk, I will provide an overview of diffusion models' key features and highlight their practical...

130. Off-Shell Processes from Neural Networks

Mathias Kuschick

07/11/2023, 14:15

Generative: Partons and Phase Space

For Monte Carlo event generators simulating events with full inclusion of off-shell effects is a computationally very costly task. In the talk, a method making use of modern machine learning techniques is presented that enables the modelling of full off-shell effects. Using this method as a surrogate for simulations, we expect significant improvements in the feasibility of high-precision event...

24. CaloDiffusion with GLaM for High Fidelity Calorimeter Simulation

Kevin Pedro (Fermi National Accelerator Lab. (US))

07/11/2023, 14:30

Generative: Diffusion Models

Generative machine learning models are a promising avenue to resolve computing challenges by replacing intensive full simulations of particle detectors. We introduce CaloDiffusion, a denoising diffusion model that generates calorimeter showers, trained on the public CaloChallenge datasets. Our algorithm employs 3D cylindrical convolutions that take advantage of symmetries in the underlying...

78. High multiplicity with JetGPT

Jonas Spinner

07/11/2023, 14:30

Generative: Partons and Phase Space

Generative networks are promising tools in fast event generation for the LHC, yet struggle to meet the required precision when scaling up to large multiplicities. We employ the flexibility of autoregressive transformers to tackle this challenge, focusing on Z and top quark pair production with additional jets. In order to further increase precision, we use classifiers to reweight the generated...

95. Diffusion Models for the LHC

Sofia Palacios Schweitzer (ITP, University Heidelberg)

07/11/2023, 14:45

Generative: Diffusion Models

Given the recent success of diffusion models in image generation, we study their applicability to generating LHC phase space distributions. We find that they achieve percent level precision comparable to INNs. To further enhance the interpretability of our results we quantify our training uncertainty by developing Bayesian versions. In this talk, diffusion models are introduced and discussed...

60. Generate parton-level events from reconstructed events with Conditional Normalizing Flows

Davide Valsecchi (ETH Zurich (CH))

07/11/2023, 14:45

Generative: Partons and Phase Space

In High Energy Physics, generating physically meaningful parton configurations from a collision reconstructed within a detector is a critical step for many complex analysis tasks such as the Matrix Element Method computation and Bayesian inference on parameters of interest. This contribution introduces a novel approach that employs generative machine learning architectures, Transformers...

90. CaloClouds: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation

Erik Buhmann (Hamburg University (DE))

07/11/2023, 15:00

Generative: Diffusion Models

Simulating showers of particles in highly-granular detectors is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models would enable them to augment traditional simulations and alleviate a major computing constraint.

This work achieves a major breakthrough in this task by directly generating a...

34. MEMeNNto – Matrix Element Method with Neural Networks

Nathan Huetsch (Institut für Theoretische Physik, Universität Heidelberg)

07/11/2023, 15:00

Generative: Partons and Phase Space

The matrix element method remains a crucial tool for LHC inference in scenarios with limited event data. We enhance our neural network-based framework, now dubbed MEMeNNto, by optimizing phase-space integration techniques and introducing an acceptance function. Additionally, employing new architectures, like transformer and diffusion models, allows us to better handle complex jet combinatorics...

52. CaloLatent: Score-based Generative Modelling in the Latent Space for Calorimeter Shower Generation

Thandikire Madula (University College London)

07/11/2023, 15:15

Generative: Diffusion Models

The simulation of particle interactions with detectors plays a central role in many high energy physics experiments. In the simulation pipeline, the most computationally expensive process is calorimeter shower generation. Looking into the future, as the size and granularity of calorimeters increase and we approach the high luminosity operational phase of the LHC, the severity of the simulation...

17. The MadNIS Reloaded

Theo Heimel (Heidelberg University)

07/11/2023, 15:15

Generative: Partons and Phase Space

Theory predictions for the LHC require precise numerical phase-space integration and generation of unweighted events. We combine machine-learned multi-channel weights with a normalizing flow for importance sampling to improve classical methods for numerical integration. By integrating buffered training for potentially expensive integrands, VEGAS initialization, symmetry-aware channels, and...

143. Keynote: Physics ex machina - Machine learning for fundamental physics

David Shih

07/11/2023, 16:00

Physics ex machina: Machine learning for fundamental physics

Modern machine learning is revolutionizing our understanding of big data for fundamental physics, promising to shed light on long-standing questions such as "where is the new physics" and "what is the dark matter". In this talk I will give an overview of recent, exciting developments in areas such as model-agnostic searches, fast simulation and interpretability. I will also highlight the...

140. Public Film Preview and Public Discussion (in German, not part of ML4Jets - but you are invited)

07/11/2023, 19:00

137. Machine Learning in Astrophysics and Astronomy

Caroline Heneka

08/11/2023, 09:00

Astrophysics and Astronomy

82. Mapping Dark Matter in the Milky Way using Normalizing Flows and Gaia DR3

Eric Putney (Rutgers, The State University of New Jersey)

08/11/2023, 09:30

Astrophysics and Astronomy

We present a novel, data-driven analysis of Galactic dynamics, using unsupervised machine learning -- in the form of density estimation with normalizing flows -- to learn the underlying phase space distribution of 6 million nearby stars from the Gaia DR3 catalog. Solving the collisionless Boltzmann equation with the assumption of approximate equilibrium, we calculate -- for the first time ever...

49. Bayesian Insights into the high-redshift Universe with 21cmPIE-cINN

Benedikt Schosser (Heidelberg University), Theo Heimel (Heidelberg University)

08/11/2023, 09:45

Astrophysics and Astronomy

Utilizing 21cm tomography provides a unique opportunity to directly investigate the astrophysical and fundamental aspects of early stages of our Universe's history, spanning the Epoch of Reionization (EoR) and Cosmic Dawn (CD). Due to the non-Gaussian nature of signals that trace this period of the Universe, methods based on summary statistics omit important information about the underlying...

41. PINNflation solving the dynamics of Inflation using Physics Informed Neural Nets

Lennart Röver (Heidelberg University)

08/11/2023, 10:00

Astrophysics and Astronomy

Cosmic inflation is a process in the early Universe responsible for the generation of cosmic structures. The dynamics of the scalar field driving inflation is determined by its self-interaction potential and is coupled to the gravitational dynamics of the FLRW-background. In addition, perturbations of the inflaton field can be computed by numerical solution of the so-called mode equations....

117. ML Approach to Infer Galaxy Cluster Masses from eROSITA X-ray Images

Nicolas Barón Pérez

08/11/2023, 10:15

Astrophysics and Astronomy

We have developed a neural network-based pipeline for estimating galaxy cluster masses directly from X-ray photon data, using known redshift information. Our approach involves training convolutional neural networks on eROSITA simulations, with a focus on the Final Equatorial Depth Survey (eFEDS) dataset. Unlike previous methods, our approach incorporates additional cluster information,...

37. The HEP-ML Living Review

Dr Claudius Krause (Rutgers University), Johnny Raine (Universite de Geneve (CH)), Ramon Winterhalder (UC Louvain)

08/11/2023, 11:00

Community & Datasets

We introduce the revamped HEPML Living Review: a more accessible website dedicated to the interplay of High-Energy Physics and Machine Learning. Featuring a new 'Recent' section and more anticipated features, we actively seek and encourage ongoing community input, envisioning this platform as a dynamic and continuously evolving exchange.

39. Open Data Detector: public dataset(s) for ML studies

Anna Zaborowska (CERN)

08/11/2023, 11:15

Community & Datasets

The development of techniques based on machine learning (ML) relies on the availability of datasets. Many studies are carried out within the context of particular experiments, using e.g. their simulation data. This narrows down the possibilities for collaboration as well as publication, with only limited datasets published for open access.

This gap can be bridged with the datasets produced...

76. Evaluating Equivariance for Reconstruction

Savannah Thais

08/11/2023, 11:30

Taggers & Understanding

Particle physics is governed by a number of fundamental symmetries including Lorentz symmetry, gauge symmetries of the Standard Model, and discrete symmetries like charge, parity, and time. Consequently, designing equivariant ML architectures has emerged as a popular method for incorporating physics-inspired inductive biases into ML models. In this work, we evaluate commonly cited benefits of...

4. Constituent based Quark/Gluon Jet Tagging

Samuel Jankovych (Charles University (CZ))

08/11/2023, 11:45

Taggers & Understanding

Improving the identification of jets initiated from gluon or quark will impact the precision of several analysis in the ATLAS collaboration physics program. Current identification algorithms (taggers) take as inputs high-level jet kinematic and substructure variables as the number of tracks associated to the jet or the jet width. We present a novel approach to tag quark- and gluon-initiated...

97. Quark versus gluon tagging in CMS Open Data with CWoLa and TopicFlow

Ayodele Ore

08/11/2023, 12:00

Taggers & Understanding

Tools for discriminating quark and gluon jets are of key importance at the LHC. Methods that train directly on real data are well motivated due to both the ambiguity of parton labels and the potential for mismodelled jet substructure in Monte Carlo. This talk presents a study of weakly-supervised learning applied to Z+jet and dijet events in CMS Open Data. Using CWoLa classifiers, we...

138. ML for jets and beyond jets

Huilin Qu (CERN)

08/11/2023, 14:00

Energy Correlators, Safety & Symmetry

72. PELICAN Update: Equivariance, Explainability, and Robustness in Jet ML

Timothy Hoffman

08/11/2023, 14:30

Energy Correlators, Safety & Symmetry

While the plethora of recent machine learning solutions to particle physics tasks have improved statistical power over hand-crafted methods, they often discount the importance and impact of explainability and the theoretical foundations the problems which they are used to address. This talk will present a comprehensive description of the latest version of the PELICAN network, a permutation and...

116. Particle Transformer with built-in IRC safety

Congqiao Li (Peking University (CN))

08/11/2023, 14:45

Energy Correlators, Safety & Symmetry

Top-performing jet networks often compromise infrared and collinear (IRC) safety, leading to a dilemma between pursuing high experimental performance and good theoretical interpretability. In this talk, we present an innovative modification of the classic Transformer self-attention block (whose token is per-particle input) to ensure full IRC safety. By integrating this recipe into Particle...

36. Combining Energy Correlators with Machine Learning

Katherine Fraser (Harvard University)

08/11/2023, 15:00

Energy Correlators, Safety & Symmetry

Energy correlators, which are are correlation functions of the energy flow operator, are theoretically clean observables which can be used to improve various measurements. In this talk, we discuss ongoing work exploring the benefits of combining them with Machine Learning.

44. SPECTER: Efficient Evaluation of the Spectral EMD

Rikab Gambhir (MIT)

08/11/2023, 15:15

Energy Correlators, Safety & Symmetry

The Energy Mover's Distance (EMD) has seen use in collider physics as a metric between events and as a geometric method for defining IRC-safe observables. Recently, the spectral EMD (SEMD) has been proposed as a more analytically tractable alternative to the EMD. In this work, we obtain a closed-form expression for the $p = 2$ SEMD metric between events, removing the need to numerically solve...

46. Back to the Roots: Tree-Based Algorithms for Weakly Supervised Anomaly Detection

Marie Hein (RWTH Aachen University)

08/11/2023, 16:00

Anomalies

Weakly supervised methods have emerged as a powerful tool for model agnostic anomaly detection at the LHC. While these methods have shown remarkable performance on specific signatures such as di-jet resonances, their application in a more model-agnostic manner requires dealing with a larger number of potentially noisy input features. We show that neural networks struggle with noisy input...

112. Classifying the CP properties of the ggH coupling in H+2j production

Henning Bahl

08/11/2023, 16:00

Measurements & Observables

The Higgs-gluon interaction is crucial for LHC phenomenology. To improve the constraints on the CP structure of this coupling, we investigate Higgs production with two jets using machine learning. In particular, we exploit the CP sensitivity of the so far neglected phase space region that differs from the typical vector boson fusion-like kinematics. Our results suggest that significant...

129. Returning CP-Observables to the Frames they Belong

Jona Ackerschott

08/11/2023, 16:15

Measurements & Observables

Optimal kinematic observables are often defined in specific frames and then approximated at the reconstruction level. We show how multi-dimensional unfolding methods allow us to reconstruct these observables in their proper rest frame and in a probabilistically faithful way. We illustrate our approach with a measurement of a CP-phase in the top Yukawa coupling. Our method makes use of key...

53. Robust Anomaly Detection in the Presence of Irrelevant Features

Yik Chuen San

08/11/2023, 16:15

Anomalies

Recent data-driven anomaly detection methods, such as CWoLA and ANODE, have shown promising results. However, they all suffer from performance degradation when irrelevant features are included. We demonstrate how these methods can be made robust even when the dataset is dominated by irrelevant features. The key idea is to employ Boosted Decision Tree (BDT)-based algorithms for...

20. Drapes: Diffusion for weak supervision

Mr Matthew Leigh (University of Geneva)

08/11/2023, 16:30

Anomalies

We employ the diffusion framework to generate background enriched templates to be used in a downstream Anomaly Detection task (generally with CWoLa). We show how Drapes can provide an analogue to many different methods of template generation, common in literature, and show good performance on the public RnD LHCO dataset.

14. End-To-End Latent Variational Diffusion Models for Unfolding LHC Events

Kevin Thomas Greif (University of California Irvine (US))

08/11/2023, 16:30

Measurements & Observables

High-energy collisions at the Large Hadron Collider (LHC) provide valuable insights into open questions in particle physics. However, detector effects must be corrected before measurements can be compared to certain theoretical predictions or measurements from other detectors. Methods to solve this inverse problem of mapping detector observations to theoretical quantities of the underlying...

83. Deep learning assisted unbinned measurements of jet substructure observables with the H1 detector

Vinicius Massami Mikuni (Lawrence Berkeley National Lab. (US))

08/11/2023, 16:45

Measurements & Observables

The radiation pattern within quark- and gluon-initiated jets (jet substructure) is used extensively as a precision probe of the strong force and for optimizing event generators for particle physics. Jet substructure measurements in electron-proton collisions are of particular interest as many of the complications present at hadron colliders are absent.

In this contribution, a detailed study...

5. The Interplay of Machine Learning–based Resonant Anomaly Detection Methods

Radha Mastandrea (University of California, Berkeley)

08/11/2023, 16:45

Anomalies

Machine learning--based anomaly detection (AD) methods are promising tools for extending the coverage of searches for physics beyond the Standard Model (BSM). One class of AD methods that has received significant attention is resonant anomaly detection, where the BSM is assumed to be localized in at least one known variable. While there have been many methods proposed to identify such a BSM...

74. Exploring the universality of jet quenching via Bayesian inference

Alexandre Falcão (University of Bergen)

08/11/2023, 17:00

Measurements & Observables

Experimental data on a wide range of jet observables measured in heavy ion collisions provide a rich picture of the modification of jets as perturbative probes and of the properties of the created quark-gluon plasma. However, their interpretation is often limited by the assumptions of specific quenching models, and it remains a challenge to establish model-independent statements about the...

128. Full Phase Space Resonant Anomaly Detection

Cedric Ewen

08/11/2023, 17:00

Anomalies

Physics beyond the Standard Model that is resonant in one or more dimensions has been the subject of many anomaly detection studies. This resonant anomaly detection is well-suited for weakly supervised machine learning, where sideband information can be used to generate synthetic datasets representing the Standard Model background. One effective strategy is to learn a conditional generative...

1. Apples to Apples in Jet Quenching

João A. Gonçalves (LIP - Lisbon / IST - Universidade de Lisboa)

08/11/2023, 17:15

Measurements & Observables

Progress in the theoretical understanding of parton branching dynamics that occurs within an expanding QGP relies on detailed and fair comparisons with experimental data for reconstructed jets. Such validation is only meaningful when the computed object, be it analitically or via event generation, accounts for the complexity of experimentally reconstructed jets. The reconstruction of jets in...

92. Combining resonant and tail-based anomaly detection

Gerrit Bickendorf (Universität Bonn)

08/11/2023, 17:15

Anomalies

In many well-motivated models of the electroweak scale, cascade decays of new particles can result in highly boosted hadronic resonances (e.g. $Z/W/h$). This can make these models rich and promising targets for recently developed resonant anomaly detection methods powered by modern machine learning. We demonstrate this using the state-of-the-art CATHODE method applied to supersymmetry...

86. Non-resonant Anomaly Detection with Background Extrapolation

Kehang Bai (University of Oregon (US))

09/11/2023, 09:00

Anomalies

Searching for non-resonant signals at the LHC is a relatively underexplored, yet challenging approach to discover new physics. These signals could arise from off-shell effects or final states with significant missing energy. This talk explores the potential of using weakly supervised anomaly detection to identify new non-resonant phenomena at the LHC. Our approach extends existing resonant...

68. R-ANODE

Ranit Das (Rutgers University)

09/11/2023, 09:15

Anomalies

We present improvements to model agnostic resonant anomaly detection based on normalizing flows.

132. Anomaly Detection in Collider Physics via Factorized Observables

Raymond Wynne (MIT)

09/11/2023, 09:30

Anomalies

To maximize the discovery potential of high-energy colliders, experimental searches should be sensitive to unforeseen new physics scenarios. This goal has motivated the use of machine learning for unsupervised anomaly detection. In this paper, we introduce a new anomaly detection strategy called FORCE: factorized observables for regressing conditional expectations. Our approach is based on the...

127. Unsupervised tagging of semivisible jets with normalized autoencoders in CMS

Florian Eble (ETH Zurich (CH))

09/11/2023, 09:45

Anomalies

Semivisible jets are a novel signature of dark matter scenarios where the dark sector is confining and couples to the Standard Model via a portal. They consist of jets of visible hadrons intermixed with invisible stable particles that escape detection. In this work, we use normalized autoencoders to tag semivisible jets in proton-proton collisions at the CMS experiment. Unsupervised models are...

104. Ultra-fast generation of Air Shower Images for Imaging Air Cherenkov Telescopes with Generative Adversarial Networks

Christian Elflein (Erlangen Centre for Astroparticle Physics)

09/11/2023, 10:00

Generative

The development of precise and computationally efficient simulations is a central challenge in modern physics. With the advent of deep learning, new methods are emerging from the field of generative models. Recent applications to the generation of calorimeter images showed promising results motivating the application in astroparticle physics. In this contribution, we introduce a...

113. ParticleGrow: Event by event simulation of heavy-ion collisions via autoregressive point cloud generation

Manjunath Omana Kuttan (Frankfurt Institute for Advanced Studies)

09/11/2023, 10:15

Generative

The properties of hot and/or dense nuclear matter are studied in the laboratory via Heavy-Ion Collisions (HIC) experiments. Of particular interest are the intermediate energy heavy-ion collisions that create strongly interacting matter of moderate temperatures and high densities where interesting structures in the QCD phase diagram such as a first order phase transition from a gas of hadrons...

102. caloutils - Utilities and Metrics for Generative Models of Calorimeter Showers

Mr Moritz Scham (Deutsches Elektronen-Synchrotron (DE))

09/11/2023, 11:00

Generative

caloutils is a Python package built to simplify and streamline the handling, processing, and analysis of 4D point cloud data derived from calorimeter showers in high-energy physics experiments. The package includes tools to map between continuous point clouds and discrete calorimeter cells.
Furthermore, the library contains models for evaluating the performance of generative models of...

67. Understanding generative networks via classifier weight distributions

Luigi Favaro

09/11/2023, 11:15

Generative

Well-trained classifiers and their complete weight distributions provide us with a well motivated and practicable method to test generative networks in particle physics. I will illustrate their benefits for distribution-shifted jets, calorimeter showers, and reconstruction level events. In all cases, the classifier weights make for a powerful test of the generative network, identify potential...

38. Level up your performance calculation of the fast shower simulation model

Anna Zaborowska (CERN)

09/11/2023, 11:30

Generative

Due to the large computing resources spent on the detailed (full) simulation of particle transport in the HEP experiments, many efforts have been undertaken to parametrise the detector response. In particular, particle showers developing in the calorimeters are typically the most time-consuming component of simulation, hence their parameterisation is of primary focus.

Fast shower simulation...

29. The New Physics Learning Machine: machine learning for goodness-of-fit via Neyman—Pearson testing

Dr Marco Letizia (MaLGa Center, Università di Genova and INFN)

09/11/2023, 11:45

Generative

In this talk I will present a recent strategy to perform a goodness-of-fit test via two-sample testing, powered by machine learning. This approach allows to evaluate the discrepancy between a data sample of interest and a reference sample, in an unbiased and statistically sound fashion. The model leverages the ability of classifiers to estimate the density ratio of the data-generating...

33. The Fast Calorimeter Simulation Challenge 2022

Dr Claudius Krause (Rutgers University)

09/11/2023, 12:00

Generative

I will summarize the results of the CaloChallenge, a HEP community challenge on generating calorimeter showers with deep generative models that took place in 2022/2023.

106. The DL Advocate: Playing the devil's advocate with hidden systematic uncertainties

Andrea Mauri (Imperial College (GB))

09/11/2023, 14:00

Uncertainties, Calibration & Theory

We propose a new method based on machine learning to play the devil's advocate and investigate the impact of unknown systematic effects in a quantitative way. This method proceeds by reversing the measurement process and using the physics results to interpret systematic effects under the Standard Model hypothesis.
We explore this idea with two alternative approaches, one relies on a...

69. Systematic Effects in Jet Tagging Performance for the ATLAS Detector

Kevin Thomas Greif (University of California Irvine (US))

09/11/2023, 14:15

Uncertainties, Calibration & Theory

Machine learning based jet tagging techniques have greatly enhanced the sensitivity of measurements and searches involving boosted final states at the LHC. However, differences between the Monte-Carlo simulations used for training and data lead to systematic uncertainties on tagger performance. This talk presents the performance of boosted top and W boson taggers when applied on data sets...

103. Evaluating Neural Network Uncertainty Estimation with Inconsistent Training Data

Giovanni De Crescenzo

09/11/2023, 14:30

Uncertainties, Calibration & Theory

Neural Networks coupled with a Monte Carlo method can be used to perform regression in the presence of incomplete information. A methodology based on this idea has been developed for the determination of parton distributions, and a closure testing methodology can be used in order to verify the reliability of the uncertainty in the results.
A relevant question in this context is what happens...

120. Generalization Properties of Jet Classification

Sebastian Guido Bieringer (Hamburg University)

09/11/2023, 14:45

Uncertainties, Calibration & Theory

Deep neural network based classifiers allow for efficient estimation of likelihood ratios in high dimensional spaces. Classifier-based cuts are thus being used to process experimental data, for example in top tagging. To efficiently investigate new theory, it is essential to estimate the behavior of these cuts efficiently. We suggest circumventing the full simulation of the experimental setup...

99. Deciphering the Structure of EFTs from String Theory using JAX and Reinforcement Learning

Dr Andreas Schachner (Ludwig-Maximilians-Universität München)

09/11/2023, 15:00

Uncertainties, Calibration & Theory

Applications of Machine Learning to physics beyond the Standard Model are becoming increasingly invaluable for theorists. As a leading proposal for a theory of quantum gravity, string theory gives rise to a plethora of 4-dimensional EFTs upon compactification, the so-called string landscape. For decades, a prohibiting factor in analysing these EFTs has been the computational cost of standard...

84. Towards a phenomenological understanding of neural networks

Samuel Tovey (University of Stuttgart)

09/11/2023, 15:15

Uncertainties, Calibration & Theory

Neural networks are a powerful tool for an ever-growing list of tasks. However, their enormous complexity often complicates developing theories describing how these networks learn. In our recent work, inspired by the development of statistical mechanics, we have studied the use of collective variables to explain how neural networks learn, specifically, the von Neumann entropy and Trace of the...

101. Machine Learning to Understand String Theory EFTs

Dr Sven Krippendorf (LMU Munich)

09/11/2023, 15:30

Uncertainties, Calibration & Theory

This talk will be about our work on using machine learning to understand Calabi-Yau metrics. These extra-dimensional metrics determine aspects of the low-energy EFTs arising from string theory which have been unavailable for several decades prior to works using machine learning methods.

12. Cluster Scanning

Mr Ivan Oleksiyuk (UNIGE)

09/11/2023, 16:15

Anomalies

We propose a new model independent method of new physics searches called cluster scanning (CS). It utilises
k-means algorithm to perform clustering in the space of low-level event or jet observables, and separates
potentially anomalous clusters to construct the anomaly rich region from the rest that form the anomaly
poor region. The spectra of the invariant mass in these two regions are...

42. Anomaly Detection in High Energy Physics via Non-Gaussian Variational Autoencoders

Thomas Dartnall Stern (University of Cape Town (ZA))

09/11/2023, 16:30

Anomalies

In particle physics, the search for phenomena outside the well-established predictions of the Standard Model (SM) is of great importance. For more than four decades, the SM has been the established theory of fundamental particles and their interactions. However, some aspects of nature remain elusive to the explanatory power of the SM. Thus, researchers' attention turns to the pursuit of new...

100. Quantum anomaly detection in the latent space of proton collision events at the LHC

Vasilis Belis (ETH Zurich (CH))

09/11/2023, 16:45

Anomalies

Exploring innovative methods and emerging technologies holds the promise of enhancing the capabilities of LHC experiments and contributing to scientific discoveries. In this work, we propose a new strategy for anomaly detection at the LHC based on unsupervised quantum machine learning algorithms. To accommodate the constraints on the problem size dictated by the limitations of current quantum...

131. Binary Discrimination at Next-to-Leading Order

Andrew Larkoski (UCLA)

09/11/2023, 17:20

Remote Discussion

Binary discrimination between well-defined signal and background datasets is a problem of fundamental importance in particle physics. In this talk, I present a first theoretical study of binary discrimination when the likelihood ratio is infrared and collinear safe, and derive expressions necessary for prediction of the ROC curve at next-to-leading order in the strong coupling. As an example...

81. Scalar Field Theories via Neural Networks at Initialization

Anindita Maiti (Perimeter Institute for Theoretical Physics)

09/11/2023, 17:25

Remote Discussion

Neural Networks (NN), the backbones of Deep Learning, create field theories through their output ensembles at initialization. Certain limits of NN architecture give rise to free field theories via Central Limit Theorem (CLT), whereas other regimes give rise to weakly coupled, and non-perturbative field theories, via small, and large deviations from CLT. I will present a systematic construction...

96. Learning Broken Symmetries with Encouraged Invariance

Daniel Whiteson (University of California Irvine (US)), Edmund Witkowski (UCI)

09/11/2023, 17:30

Remote Discussion

Recognizing symmetries in data allows for significant boosts in neural network training. In many cases, however, the underlying symmetry is present only in an idealized dataset, and is broken in the training data, due to effects such as arbitrary and/or non-uniform detector bin edges. Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the...

47. HEP ML Lab — An end-to-end framework for signal vs background analysis in high energy physics

Jing Li (Dalian University of Technology, Liaoning, China)

09/11/2023, 17:35

Remote Discussion

We have developed an end-to-end data analysis framework, HEP ML Lab (HML), based on Python for signal-background analysis in high-energy physics research. It offers essential interfaces and shortcuts for event generation, dataset creation, and method application.

With the HML API, a large volume of collision events can be generated in sequence under different settings. The representations...

118. Perturbatively Regularized Neural Networks

Chase Owen Shimmin (Yale University (US))

09/11/2023, 17:40

Remote Discussion

We present a class of Neural Networks which extends the notion of Energy Flow Networks (EFNs) to higher-order particle correlations. The structure of these networks is inspired by the Energy-Energy Correlators of QFT, which are particularly robust against non-perturbative corrections. By studying the response of our models to the presence and absence of non-perturbative hadronization, we can...

70. Giving events a new shape : measurements of multijet event isotropy at ATLAS using optimal transport

Matt LeBlanc (University of Manchester (GB))

10/11/2023, 09:00

Results, Observables & Techniques

A measurement of novel event shapes quantifying the isotropy of collider events is presented, made using 140 fb$^{−1}$ of proton-proton collisions with $\sqrt{s}$=13 TeV centre-of-mass energy recorded with the ATLAS detector at CERN's Large Hadron Collider. These event shapes are defined as the Energy-Mover's Distance between collider events and isotropic reference geometries, evaluated by...

142. Sensitivity Studies for Search of B+ → K∗+ νν using Lorentz Equivariant Neural Networks at the Belle II Experiment

Caspar Schmitt

10/11/2023, 09:15

Results, Observables & Techniques

109. DeGeSim: Conditional Denoising Diffusion Probabilistic Models as Multi-Dimensional Density Mappers for Continuous and Discrete State Spaces

Judith Katzy (Deutsches Elektronen-Synchrotron (DE)), Stephen Jiggins (Deutsches Elektronen-Synchrotron (DE))

10/11/2023, 09:30

Results, Observables & Techniques

As the performance of the Large Hadron Collider (LHC) continues to improve in terms of energy reach and instantaneously luminosity, ATLAS faces an increasingly challenging environment. High energy proton-proton ($pp$) interactions, known as hard scatters, are produced in contrast to low energy inelastic proton-proton collisions referred to as pile-up. From the perspective of data analyses,...

10. Jet formation with Chebyshev Polynomials

Henry Day-Hall (Czech Technical University in Prague (CZ))

10/11/2023, 09:45

Results, Observables & Techniques

Jet formation algorithms that utilise eigenvalues of the similarity matrix offer a innovative take on the definition of a jet. This is referred to as spectral clustering. It solves the clustering problem in a non-greedy manner, and so may find more optimal solutions that straightforward agglomerative algorithms. However, the eigenvalue problem is computationally expensive, so in this study...

65. Weakly supervised training for optimal transport pileup mitigation strategies at hadron colliders

Nathan Suri Jr (Yale University (US))

10/11/2023, 10:00

Results, Observables & Techniques

On average, during Run 2 of the Large Hadron Collider (LHC), 30-50 simultaneous vertices yielding charged and neutral showers, otherwise known as pileup, were recorded per event. This number is expected to only increase at the High Luminosity LHC with predicted values as high as 200. As such, pileup presents a salient problem that, if not checked, hinders the search for new physics as well as...

58. Model-agnostic search for dijet resonances with anomalous jet substructure with the CMS detector

Louis Moureaux (Hamburg University (DE))

10/11/2023, 10:15

Results, Observables & Techniques

We present a model-agnostic search for new physics in the dijet final state using five different novel machine-learning techniques. Other than the requirement of a narrow dijet resonance, minimal additional assumptions are placed on the signal hypothesis. Signal regions are obtained utilizing multivariate machine learning methods to select jets with anomalous substructure. A collection of...

136. Theory Closure

Michael Kramer (Rheinisch Westfaelische Tech. Hoch. (DE))

10/11/2023, 11:00

Closing

141. Closing and Final Remarks

Gregor Kasieczka (Hamburg University (DE))

10/11/2023, 11:30

Closing

144. Announcement of ML4Jets 2024

10/11/2023, 11:35

Closing

64. How important is a realistic calorimeter model for machine learning jet substructure?

Sanmay Ganguly (University of Tokyo (JP)), Etienne Dreyer (Weizmann Institute of Science (IL))

Remote Discussion

Neural network models that rely on jet substructure are commonly trained assuming jet constituents at truth level or smeared by parameterized detector response. However, the performance in such simplified circumstances may translate poorly to actual collider experiments. We investigate the impact by comparing large-R jet tagging using smeared particle-level jets versus jets built using...

139. Invited Talk: Low Latency and Anomaly Detection

Thea Aarrestad (ETH Zurich (CH))

Anomalies

125. Jet Calibration with Uncertainty-Aware Precision Networks

Mr Lorenz Vogel (Heidelberg University)

Uncertainties, Calibration & Theory

Abstract: Utilizing modern ML-techniques, we address the challenge of multi-dimensional correlated calibration of topological calorimeter-cell clusters (topo-clusters). Our Bayesian neural network (BNN) approach not only yields a continuous, unbinned calibration function that improves performance relative to the standard calibration but also provides single-cluster uncertainties. A boosted...

111. Machine learning with open data and experiment-independent software tools for AI Safety

Annika Stein

Community & Datasets

A software suite to prepare (CMS) Open Data for machine learning purposes is introduced. In this presentation, different approaches and their suitability to extract low-level information will be compared. The full chain is implemented with the help of high-performance computing infrastructures, and a study of available data formats and data tiers is conducted. As a proof-of-concept, the work...

75. Measurement of Track Functions and their Renormalization Group Flows in ATLAS Run 2 Data

Jingjing Pan (Yale University (US))

Remote Discussion

A new measurement of non-perturbative track functions, or, the ratio of a jet's transverse momentum carried by its charged constituents to its complete transverse momentum, is performed in 140 fb$^{-1}$ of proton–proton collisions with $\sqrt{s}=13$ TeV centre-of-mass energy recorded with the ATLAS detector at CERN’s Large Hadron Collider. The measurement is made using dijet events,...

27. ML-Based Top Taggers: Performance, Uncertainty and Impact of Tower & Tracker Data Integration

Dr Kirtiman Ghosh (Institute Of Physics, Bhubaneswar), Mr Rameswar Sahu

Remote Discussion

Machine learning algorithms have the capacity to discern intricate features directly from raw data. We demonstrated the performance of top taggers built upon three machine learning architectures: a BDT that uses jet-level variables (high-level features, HLF) as input, while a CNN (ResNet) trained on the jet image, and a GNN (LorentzNet) trained on the particle cloud representation of a jet...

108. NFLikelihood: Unsupervised Machine Learning LHC likelihoods with Normalizing Flows.

Humberto Alonso Reyes Gonzalez (University of Genoa)

Results, Observables & Techniques

Full statistical models encapsulate the complete information of an experimental result, including the likelihood function given observed data. Their proper publication is of vital importance for a long lasting legacy of the LHC. Major steps have been taken towards this goal; a notable example being ATLAS release of statistical models with the pyhf framework. However, even the likelihoods are...

9. Out-Of-Distribution Multi-Set Generation with Context Extrapolation

Hosein Hashemi (LMU Munich)

Remote Discussion

Addressing the challenge of Out-of-Distribution (OOD) multi-set generation, this paper introduces YonedaVAE, a novel equivariant deep generative model inspired by Category Theory, introducing Yoneda-Pooling mechanism. This approach presents a learnable Yoneda Embedding to encode the relationships between objects in a category, providing a dynamic and generalizable representation of complex...

91. Searching for stellar streams with machine learning

Anna Maria Cecilia Hallin (University of Hamburg), Dr Claudius Krause (Rutgers University), David Shih

Astrophysics and Astronomy

Some machine learning methods that have been developed for particle physics applications are actually completely general with regards to the data. In this talk, I will show how ANODE and CATHODE, originally created to search for anomalies in particle physics, can be used to search for stellar streams in the Milky Way using data from the Gaia space telescope. Stellar streams are important...