ML4Jets2021

Contribution List

86. SO(3)-equivariant Neural Network for b-tagging

Ema Catalina Smith

06/07/2021, 09:00

New architectures

Jets originating from bottom quarks, b-jets, are of particular interest in high energy physics. While b-jets are similar to other jets, they have certain qualities that present unique challenges in the context of machine learning. Generally, there is an underlying rotational symmetry of the particles about a jet’s axis. However, in the case of b-jets, some of the most discriminating...

69. Equivariant energy flow networks for jet tagging

Ayodele Ore (The University of Melbourne)

06/07/2021, 09:20

New architectures

The Energy Flow Network (EFN) is a neural network architecture that represents jets as point clouds and enforces infrared and collinear (IRC) safety on its outputs. In this talk, I will introduce a new variant of the EFN architecture based on the Deep Sets formalism, incorporating permutation-equivariant layers. I will discuss the conditions under which IRC safety can be maintained in the new...

49. SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention

Michael James Fenton (University of California Irvine (US))

06/07/2021, 09:40

New architectures

One of the most ubiquitous challenges in analyses at the LHC is event reconstruction, whereby heavy resonance particles (such as top quarks, Higgs bosons, or vector bosons) must be reconstructed from the detector signatures left behind by their decay products. This is particularly challenging when all decay products have similar or identical signatures, such as all-jet events. Existing methods...

89. Particle Convolution for Jets

Chase Owen Shimmin (Yale University (US))

06/07/2021, 10:00

New architectures

We introduce the Particle Convolution Network (PCN), a new type of equivariant neural network layer suitable for many tasks in jet physics. The particle convolution layer can be viewed as an extension of Deep Sets and Energy Flow network architectures, in which the permutation-invariant operator is promoted to a group convolution. While the PCN can be implemented for various kinds of...

14. Linearized Optimal Transport for Jet Physics

Ms Tianji Cai (Department of Physics, University of California, Santa Barbara)

06/07/2021, 10:20

New architectures

Optimal Transport has been applied to jet physics for the computation of distance between collider events. Here we generalize the Energy Mover’s Distance to include both the balanced Wasserstein-2 (W2) distance and the unbalanced Hellinger-Kantorovich (HK) distance. Whereas the W2 distance only allows for mass to be transported, the HK distance allows mass to be transported, created and...

22. Supervised Attention for Jet Classification

Jonathan Shlomi (Weizmann Institute of Science (IL))

06/07/2021, 10:40

New architectures

Secondary vertex reconstruction is a key intermediate step in building powerful jet classifiers. We use a neural network to perform vertex finding inside jets in order to improve classification performance. This can be thought of as a supervised attention mechanism - directing the classifier towards the relevant information inside the jet. We show supervised attention outperforms an identical...

84. The information content of quenched jets

James Mulligan (University of California, Berkeley (US))

06/07/2021, 11:00

New architectures

In high energy heavy-ion collisions the substructure of jets is modified compared to that in proton-proton collisions due to the presence of the quark-gluon plasma (QGP). This modification of jets in the QGP is called ''jet quenching''. We employ machine learning techniques to quantify how much information about this process is within the substructure observables. We formulate the question as...

85. Identifying Heavy-Flavor Jets Using Vectors of Locally Aggregated Descriptors

Jitka Mrazkova

06/07/2021, 11:20

New architectures

Jets of collimated particles originating from hard scattered partons are utilized in a wide range of analyses in high energy physics. Our study is focused on identifying jets originating from heavy quarks. We introduce a novel approach to tagging heavy-flavor jets at collider experiments utilizing the information contained within jet constituents via the JetVLAD model architecture. This model...

40. A new approach to unsupervised learning in jet physics

Peter Rangi Sorrenson (Universität Heidelberg)

06/07/2021, 11:40

New architectures

TBC

57. High-dimensional Anomaly Detection with Radiative Return in e+e- Collisions

Julia Lynne Gonski (Columbia University (US))

06/07/2021, 14:00

BSM

Experiments at a future $e^{+}e^{-}$ collider will be able to search for new particles with masses below the nominal centre-of-mass energy by analyzing collisions with initial-state radiation (radiative return). We show that machine learning methods based on semisupervised and weakly supervised learning can achieve model-independent sensitivity to the production of new particles in radiative...

95. Invertible Neural Networks beyond Particle Physics

Lynton Ardizzone (Heidelberg)

06/07/2021, 14:00

ML-Assisted Measurements and Searches

Invertible Neural Networks (INNs) are an extremely versatile class of generative models. Their invertibility allows for exact modelling of proability densities, computation of information-theoretic quanities, interpretable and disentangled features, among other things. Due to these properties, INNs have seen growing adoption in recent years, especially in natural sciences and engineering...

55. CATHODE part 1: introducing a new model-agnostic search strategy for resonant new physics at the LHC

Anna Hallin (Test IDP - Rutgers, The State University of New Jerse)

06/07/2021, 14:20

BSM

We propose Classifier-based Anomaly detection THrough Outer Density Estimation (CATHODE), a new approach to search for resonant new physics at the LHC in a model-agnostic way. In CATHODE, we train a conditional density estimator on additional features in the sideband region, interpolate it into the signal region, and sample from it. This produces in a data-driven way events that follow the SM...

56. CATHODE part 2: robustness and comparison to other methods

Manuel Sommerhalder (Hamburg University (DE))

06/07/2021, 14:40

BSM

We explore the robustness of the CATHODE (Classifier-based Anomaly detection THrough Outer Density Estimation) method against correlation in the input features. We also compare CATHODE to other related approaches, specifically ANODE and CWoLa Hunting. Using the LHCO R&D dataset, we will demonstrate that in the absence of feature correlations, CATHODE outperforms both ANODE and CWoLa Hunting,...

71. Combining Neural Network predictions with Hypothesis Testing for discovery in the LHC

Michael Soughton (University of Sussex)

06/07/2021, 14:40

ML-Assisted Measurements and Searches

As the use of Machine Learning techniques become more widespread within High Energy Physics it is important to consider how the results from Neural Networks can be applied within hypothesis testing. We show how a Log-Likelihood Ratio test can be performed using the the output of Neural Network classifiers trained on different physical datasets to yield a detection significance between two...

19. Anomaly Detection in the Copula Space

Tommaso Dorigo (Universita e INFN, Padova (IT))

06/07/2021, 15:00

BSM

A unsupervised learning tool that searches for localized, overdense regions of the copula space of a multidimensional feature space is discussed. The algorithm, named RanBox, exists in two versions - one which searches multiple times in random subspaces (typically of 8 to 12 dimensions) of the feature space, and a second one (RanBoxIter) which iteratively adds dimensions to the searched space....

30. Invertible Networks or Partons to Detector and Back Again

Anja Butter

06/07/2021, 15:00

ML-Assisted Measurements and Searches

For simulations where the forward and the inverse directions have a physics meaning, invertible neural networks are especially useful. A conditional INN can invert a detector simulation in terms of high-level observables, specifically for ZW production at the LHC. It allows for a per-event statistical interpretation. Next, we allow for a variable number of QCD jets. We unfold detector effects...

35. Jet Metrics and Autoencoders

Rashmish Mishra (Harvard University)

06/07/2021, 15:20

BSM

The Energy Movers Distance was recently proposed as an advantageous metric to distinguish certain types of signals at the LHC. We explore generalizations of this distance to multiple families of signals and find similar performance anomaly detection through variational autoencoders. We investigate this connection by exploring the correlation of event distances with distances in the latent...

64. Towards a new generation of PDFs using ML

Roy Stegeman (University of Milan)

06/07/2021, 15:20

ML-Assisted Measurements and Searches

We present the machine learning methodology that is the backbone of the new release of the NNPDF family of parton distribution functions. The new methodology introduces state of the art machine learning techniques such as stochastic gradient descent for neural network training which results in a major reduction in computational costs, and an automated optimization of the hyperparameters which...

31. Detecting Anomalous jets with Graph Neural Networks

Mr Vishal Singh Ngairangbam (Physical Research Laboratory)

06/07/2021, 15:40

BSM

We devise an autoencoder based strategy to facilitate anomaly detection for boosted jets, employ-
ing Graph Neural Networks (GNNs) to do so. To overcome known limitations of GNN autoencoders,
we design a symmetric decoder capable of simultaneously reconstructing edge features and node fea-
tures. Focusing on latent space based discriminators, we find that such setups provide a...

45. Emerging techniques for sampling, searching, and summing over the combinatorially large space of shower histories

Sebastian Macaluso (New York University)

06/07/2021, 15:40

ML-Assisted Measurements and Searches

A central challenge in jet physics is that the evolution of the jet is an unobserved, latent process. In a semi-classical parton shower, this corresponds to a sequence of 1-to-2 splittings that form a tree-like showering history. Framing jet physics in probabilistic terms is attractive as it provides a principled framework to think about tasks as diverse as clustering, classification, parton...

34. Review of the Dark Machine Anomaly Score Challenge I

Joe Davies

06/07/2021, 16:00

BSM

We describe the outcome of a data challenge conducted as part of the Dark Machines Initiative and the Les Houches 2019 workshop on Physics at TeV colliders. The challenge aims at detecting signals of new physics at the LHC using unsupervised learning algorithms. We define and describe a large benchmark dataset, consisting of > 1 Billion simulated LHC events. We then review a wide range of...

44. Tuning the parton shower parameters with the marginal likelihood

Matthew Drnevich (New York University (US))

06/07/2021, 16:00

ML-Assisted Measurements and Searches

Tuning parton shower models to data is an important task for HEP experiments. We are performing exploratory research for what tuning the parton shower might look like if the parton shower were described by a generative model with a tractable likelihood, which might be implemented with a hybrid of theoretically-motivated components or generic neural network components. For this work we consider...

42. Computing the exact optimal classifier for Ginkgo jets

Lauren Greenspan (NYU)

06/07/2021, 16:20

ML-Assisted Measurements and Searches

In the last several years, the ML4Jets community has worked to improve performance for jet tagging and performed a number of comparisons of different architectures for jet tagging and other tasks. We have seen that combining multiple classifiers together into a meta-tagger or an ensemble improves performance. But is there still room for improvement? In other words, are we approaching the...

98. Review of the Dark Machine Anomaly Score Challenge II

Bryan Ostdiek (Harvard University)

06/07/2021, 16:20

BSM

We describe the outcome of a data challenge conducted as part of the Dark Machines Initiative and the Les Houches 2019 workshop on Physics at TeV colliders. The challenge aims at detecting signals of new physics at the LHC using unsupervised learning algorithms. We define and describe a large benchmark dataset, consisting of > 1 Billion simulated LHC events. We then review a wide range of...

62. Boosting new physics sensitivity with Variational Autoencoders

Kinga Anna Wozniak (University of Vienna (AT))

06/07/2021, 16:40

BSM

We show how an anomaly detection algorithm could be integrated in a typical search for new physics in events with jets at the CERN Large Hadron Collider (LHC). We assume that an anomaly detection algorithm is given, trained to identify rare jet types, such as jets originating from the decay of a highly boosted massive particle. We demonstrate how this algorithm could be integrated in a search...

77. Parametrized classifiers for optimal EFT sensitivity

Alfredo Glioti (EPFL - Ecole Polytechnique Federale Lausanne (CH))

06/07/2021, 16:40

ML-Assisted Measurements and Searches

We study unbinned multivariate analysis techniques, based on Statistical Learning, for indirect new physics searches at the LHC in the Effective Field Theory framework. We focus in particular on high-energy ZW production with fully leptonic decays, modeled at different degrees of refinement up to NLO in QCD. We show that a considerable gain in sensitivity is possible compared with current...

46. Autoencoders for unsupervised anomaly detection in high energy physics

Thorben Finke

06/07/2021, 17:00

BSM

Autoencoders have been introduced in high energy physics as a promising tool for model-independent new physics searches. As a benchmark scenario, we study the tagging of top jet images in a background of QCD jet images. Although we reproduce the positive results from the literature, we show that the standard autoencoder setup cannot be considered as a model-independent anomaly tagger by...

12. Measuring QCD Splittings with Invertible Networks

Theo Heimel (Universität Heidelberg)

06/07/2021, 17:00

ML-Assisted Measurements and Searches

QCD splittings are among the most fundamental theory concepts at the LHC. In this talk, I will show how they can be studied systematically with the help of invertible neural networks. These networks work with sub-jet information to extract fundamental parameters from jet samples. Our approach expands the LEP measurements of QCD Casimirs to a systematic test of QCD properties based on low-level...

59. Jet-based TMD measurements with H1 data, unfolded using machine-learning techniques

Miguel Ignacio Arratia Munoz (Lawrence Berkeley National Lab. (US)), Miguel Ignacio Arratia Munoz

06/07/2021, 17:20

ML-Assisted Measurements and Searches

Recently, jet measurements in DIS events close to Born kinematics have been proposed as a new probe to study transverse-momentum-dependent (TMD) PDFs, TMD fragmentation functions, and TMD evolution. We report measurements of lepton-jet momentum imbalance and hadron-in-jet correlations in high-$Q^2$ DIS events collected with the H1 detector at HERA. The jets are reconstructed with the kT...

96. Recognizing hadronic SUEP at the LHC with Unsupervised Machine Learning

Jared Barron (University of Toronto)

06/07/2021, 17:20

BSM

Models with dark showers represent one of the most challenging possibilities for new physics at the LHC. One of the most difficult examples is a novel collider signature called a Soft Unclustered Energy Pattern (SUEP), which can arise in certain BSM models with a hidden valley sector that is both pseudo-conformal and strongly coupled over a large range of energy scales. Large-angle emissions...

88. Classifier-based Anomalous Jet Tagging

Taoli Cheng (University of Montreal)

06/07/2021, 17:40

BSM

As an alternative approach (w.r.t. deep generative models) for detecting out-of-distribution samples, we explore the possibility of employing jet classifiers as anomalous jet taggers. We also discuss the advantages and limitations of different approaches.

17. Parameter Inference from Event Ensembles and the Top-Quark Mass

Katherine Fraser (Harvard University)

06/07/2021, 17:40

ML-Assisted Measurements and Searches

Measurements at colliders are often done by fitting data to simulations, which depend on many physical and unphysical parameters. One example is the top-quark mass, where parameters in simulation must be profiled when fitting the top-quark mass parameter. In particular, the dependence of top-quark mass fits on simulation parameters contributes to the error in the best measurements of the...

24. Latent Space Refinement for Deep Generative Models

Ramon Winterhalder (Universität Heidelberg)

06/07/2021, 20:00

Compression

Deep generative models are becoming widely used across science and industry for a variety of purposes. A common challenge is achieving a precise implicit or explicit representation of the data probability density. Recent proposals have suggested using classifier weights to refine the learned density of deep generative models. We extend this idea to all types of generative models and show how...

38. Compressing PDF sets using Generative Adversarial Networks

Tanjona Radonirina Rabemananjara (INFN - National Institute for Nuclear Physics)

06/07/2021, 20:20

Compression

Data compression plays a major role in the field of Machine Learning and recent works based on generative models such as Generative Adversarial Networks (GANs) have shown that deep-learning-based compression can outperform state-of-the-art classical compression methodologies. Such techniques can be adapted and applied to various areas in high energy physics, in particular to the study of the...

47. Exploring phase space with Neural Importance Sampling

Timo Janßen (Georg-August-Universität Göttingen)

06/07/2021, 20:40

Compression

Due to the expected increase in LHC data from the HL upgrade it is important to work on the efficiency of MC Event Generators in order to make theoretical predictions with the necessary precision accessible. One part of the calculation that could benefit from improvements is the generation of unweighted parton-level events. While adaptive multi-channel importance sampling combined with the...

68. Lorentz Group Equivariant Autoencoder

Zichun Hao (Univ. of California San Diego (US))

06/07/2021, 21:00

Compression

Symmetries are ubiquitous and essential in physics, and the framework to describe symmetries is group theory. The symmetry described by the Lorentz group is essential in the dynamics of all particle physics experiments. A Lorentz-group-equivariant deep neural network framework, called the Lorentz group network (LGN), has been introduced by Bogatskiy et al. and tested for performance in...

53. Combine and Conquer: Event Reconstruction with Bayesian Ensemble Neural Networks

Jack Araz (IPPP - Durham University)

07/07/2021, 09:00

Classification

Ensemble learning is a technique where multiple component learners are combined through a protocol. In this talk, we will present an Ensemble Neural Network (ENN) that uses the combined latent-feature space of multiple neural network classifiers to improve the representation of the network hypothesis. We apply this approach to construct an ENN from Convolutional and Recurrent Neural Networks...

87. Pushing the limit of jet tagging with graph neural networks

Huilin Qu (CERN)

07/07/2021, 09:20

Classification

Graph neural networks (GNNs) have shown a lot of potential for jet tagging. Recent GNN algorithms such as ParticleNet, ABCNet, and LundNet represent the state-of-the-art in various jet tagging tasks. In this talk, we present some new progress on GNN design for jet tagging. With the incorporation of edge features and optimized network architecture, the new algorithm achieves a significant...

36. Jet tagging in the Lund plane with graph networks

Dr Frederic Alexandre Dreyer (University of Oxford)

07/07/2021, 09:40

Classification

The identification of boosted heavy particles such as top quarks or vector bosons is one of the key problems arising in experimental studies at the Large Hadron Collider. In this article, we introduce LundNet, a novel jet tagging method which relies on graph neural networks and an efficient description of the radiation patterns within a jet to optimally disentangle signatures of boosted...

11. Higgs tagging with the Lund jet plane

Charanjit Kaur Khosa (University of Genova and INFN Genova)

07/07/2021, 10:00

Classification

In this talk we will present a a procedure to separate boosted Higgs bosons decaying into hadrons, from the background due to strong interactions. We employ the Lund jet plane to obtain a theoretically well-motivated representation of the jets of interest and we use the resulting images as the input to a convolutional neural network.  In particular, we consider two different decay modes of the...

82. Identifying the Quantum Properties of Hadronic Resonances using Machine Learning

Jakub Filipek (University of Washington)

07/07/2021, 10:20

Classification

With the great promise of deep learning, discoveries of new particles at the Large Hadron Collider (LHC) may be imminent. Following the discovery of a new Beyond the Standard model particle in an all-hadronic channel, deep learning can also be used to identify its quantum numbers. Convolutional neural networks (CNNs) using jet-images can significantly improve upon existing techniques to...

76. Morphology for Jet Classification

Sung Hak Lim (Rutgers University)

07/07/2021, 10:40

Classification

We introduce a morphological analysis based on a neural network analyzing the Minkowski Functionals (MFs) of pixellated jet images. The MFs describe the geometric measures of binary images, and their changes by dilation encode the jet constituents' geometric structures that appear at various angular scales. We explicitly show that this morphological analysis can be considered a constrained...

74. Boosted jet tagging in CMS

Congqiao Li (Peking University (CN))

07/07/2021, 11:00

Classification

Identification of hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks provides powerful handles to a wide range of new physics searches and Standard Model measurements at the LHC. This talk presents recent advances in boosted jet tagging algorithms in CMS. The application of novel machine-learning techniques has substantially improved the tagging performance and led to a...

3. A $W^\pm$ polarization analyzer from Deep Neural Networks

Taegyun Kim (University of Notre Dame)

07/07/2021, 11:20

Classification

We train a Convolutional Neural Network to classify longitudinally and transversely polarized hadronic $W^\pm$ using the images of boosted $W^{\pm}$ jets as input. The images capture angular and energy information from the jet constituents that is faithful to the properties of the original quark/anti-quark $W^{\pm}$ decay products without the need for invasive substructure cuts. We find that...

37. Testing Universality in various Monte Carlo Generators in Deep Learning with Application in Higgs-boson pair searches in 2HDM

Mr Yi-Lun Chung (National Tsing Hua University (TW))

07/07/2021, 11:40

Classification

It is widely known that predictions for jet substructure features vary significantly between Monte Carlo generators. This is especially true for the output of deep neural networks (NN) trained with high-dimensional feature spaces to tag the origin of a jet. However, even though the spectra of a given NN varies between generators, it could be that the function learned by different generators...

27. CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows

Dr Claudius Krause (Rutgers University)

07/07/2021, 14:00

Simulation and Generative Models

We introduce CaloFlow, a fast detector simulation framework based on normalizing flows. For the first time, we demonstrate that normalizing flows can reproduce high-granularity calorimeter simulations with extremely high fidelity, providing a fresh alternative to computationally expensive GEANT4 simulations, as well as other state-of-the-art fast simulation frameworks based on GANs and VAEs....

29. Machine learning based Particle Flow algorithm and application of super-resolution techniques

Sanmay Ganguly (Weizmann Institute of Science (IL))

07/07/2021, 14:00

Regression, Calibration, and Fast Inference

In High Energy Physics experiments Particle Flow (PFlow) algorithms are designed to provide an optimal reconstruction of the nature and kinematic properties of the particles produced within the detector acceptance during collisions. At the heart of PFlow algorithms is the ability to distinguish the calorimeter energy deposits of neutral particles from those of charged particles, using the...

90. Multi-detector geomotery modeling and Geant4 Integration

Dalila Salamani (CERN)

07/07/2021, 14:20

Simulation and Generative Models

The extensive physics program of HEP experiments relies on simulated Monte Carlo events. This simulation provides a highly detailed detector response modeling. However, this simulation dominated by the calorimeter showers becomes very slow in the context of high luminosity LHC. Collecting order of magnitude more data remains necessary to lower the statistical uncertainties. Several research...

65. Using Machine Learning for Heavy-Ion Jet $p_{\rm T}$ Reconstruction in ALICE

Hannah Bossi (Yale University (US))

07/07/2021, 14:20

Regression, Calibration, and Fast Inference

Reconstructing the jet transverse momentum ($p_{\rm T}$)is a challenging task, particularly in heavy-ion collisions due to the large fluctuating background from the underlying event. In the recent years, ALICE has developed a novel method to correct jets for this large background using machine learning techniques. This analysis intentionally does not utilize deep learning methods and instead...

60. Angular Conditioning of Deep Generative Models for Fast Simulation of High Granularity Calorimeters

Peter McKeown (Deutsches Elektronen-Synchrotron DESY)

07/07/2021, 14:40

Simulation and Generative Models

Modern high energy physics crucially relies on simulation to connect experimental observations to underlying theory. While traditional methods relying on Monte Carlo techniques produce powerful simulation tools, they prove to be computationally expensive. This is particularly true when they are applied to calorimeter shower simulation, where many particle interactions occur. The strain on...

70. Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics

Rikab Gambhir (MIT)

07/07/2021, 14:40

Regression, Calibration, and Fast Inference

A common problem that appears in collider physics is the inference of a random variable $Y$ given a measurement of another random variable $X$, and the estimation of the uncertainty on $Y$. Additionally, one would like to quantify the extent to which $X$ and $Y$ are related. We present a machine learning framework for performing frequentist maximum likelihood inference with uncertainty...

39. Fast and Accurate Electromagnetic and Hadronic Showers from Generative Models

Engin Eren (Deutsches Elektronen-Synchrotron DESY)

07/07/2021, 15:00

Simulation and Generative Models

Generative machine learning models are a promising way to efficiently amplify classical Monte Carlo generators' statistics for event simulation and generation in particle physics. The high computational cost of the simulation and the expected increase in data in the high-precision era of the LHC and at future colliders indicate that we urgently need such fast surrogate simulators. We present a...

72. ML in jet physics beyond classification

Loukas Gouskos (CERN)

07/07/2021, 15:00

Regression, Calibration, and Fast Inference

Advanced machine-learning techniques started recently to be explored by the CMS collaboration in various areas of jet physics, beyond jet classification. We present the most recent developments for the jet energy calibration and the jet mass reconstruction. In both cases novel algorithms using state-of-the-art machine-learning techniques have been developed. Significant improvement compared to...

73. AtlFast3: The next generation of fast simulation in ATLAS

Joshua Falco Beirer (CERN, Georg-August-Universitaet Goettingen (DE))

07/07/2021, 15:20

Simulation and Generative Models

AtlFast3 is the next generation of high precision fast simulation in ATLAS that is being deployed by the collaboration and will replace AtlFastII, the fast simulation tool that was successfully used until now. AtlFast3 combines a parametrization-based Fast Calorimeter Simulation and a new machine-learning based Fast Calorimeter Simulation based on Generative Adversarial Networks (GANs). The...

75. Pileup mitigation in CMS

Benedikt Maier

07/07/2021, 15:20

Regression, Calibration, and Fast Inference

At the LHC, each bunch crossings is able to create thousands of particles per collisions. Identifying a collision of interest from additional “pileup” collisions is a difficult task, requiring the development of dedicated methods. Commonly used methods are however not scalable to future LHC upgrades, where the average number of interactions will increase by almost an order of magnitude. To...

80. Fast Simulation of Jets with VAEs

Mary Touranakou (National and Kapodistrian University of Athens (GR))

07/07/2021, 15:40

Simulation and Generative Models

Typically, high-energy physics (HEP) data analysis heavily relies on the production and the storage of large datasets of simulated events. At the LHC, the end-to-end simulation workflow can require up to 50% of the available computing resources of an experiment. Speeding up the simulation process would be crucial to save resources that could be otherwise utilized.
In our study, we investigate...

48. Lightweight Jet Reconstruction as an Object Detection Task

Adrian Alan Pol (CERN)

07/07/2021, 15:40

Regression, Calibration, and Fast Inference

We apply object detection techniques based on convolutional blocks to jet reconstruction and identification at the CERN Large Hadron Collider. We use particles reconstructed through a Particle Flow algorithm to represent each event as an image composed of a calorimeter and tracker cells as input and a Single Shot Detection network, called PFJet-SSD. The network performs simultaneous...

67. Foundations of a Fast, Data-Driven, Machine-Learned Simulator

Jessica N. Howard (Department of Physics & Astronomy, UC Irvine), Jessica N. Howard (University of California Irvine (US))

07/07/2021, 16:00

Simulation and Generative Models

We introduce a novel strategy for machine-learning-based fast simulators, which is the first that can be trained in an unsupervised manner using observed data samples to learn a predictive model of detector response and other difficult-to-model transformations. Across the physical sciences, a barrier to interpreting observed data is the lack of knowledge of a detector's imperfect resolution,...

32. Measurement of Muon Energy From Radiative Losses in a Granular Calorimeter

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

07/07/2021, 16:00

Regression, Calibration, and Fast Inference

The performance demands of future particle-physics experiments investigating the high-energy frontier pose a number of new challenges, forcing us to find new solutions for the detection, identification, and measurement of final-state particles in subnuclear collisions. One such challenge is the precise measurement of muon momenta at very high energy, where the curvature provided by conceivable...

8. Deep learning jet modifications in heavy-ion collisions

Dr Yilun Du (University of Bergen)

07/07/2021, 16:20

Regression, Calibration, and Fast Inference

Jet interactions in a hot QCD medium created in heavy-ion collisions are conventionally assessed by measuring the modification of the distributions of jet observables with respect to the proton-proton baseline. However, the steeply falling production spectrum introduces a strong bias toward small energy losses that obfuscates a direct interpretation of the impact of medium effects in the...

33. Particle Cloud Generation with Message Passing GANs

Raghav Kansal (Univ. of California San Diego (US))

07/07/2021, 16:20

Simulation and Generative Models

There has been significant development recently in generative models for accelerating LHC simulations. Work on simulating jets has primarily used image-based representations, which tend to be sparse and of limited resolution. We advocate for the more natural ‘particle cloud’ representation of jets, i.e. as a set of particles in momentum space, and discuss four physics- and...

54. Matrix Element Calculations on the GPU

Joshua Isaacson (Fermilab)

07/07/2021, 16:40

Regression, Calibration, and Fast Inference

Generating large numbers of events efficiently is a major bottleneck for ML projects. As a first step towards a full-fledged event generator for modern GPUs, we investigated different recursive strategies. The GPU implementations are compared to the state-of-the-art CPU codes, showing promise for using these in other pipelines. Finally, we propose baseline implementations for the development...

83. White Box AI for parton shower development

Felix Ringer (Lawrence Berkeley National Laboratory)

07/07/2021, 16:40

Simulation and Generative Models

We present an implementation of an explainable and physics-aware machine learning model capable of inferring the underlying physics of high-energy particle collisions using the information encoded in the energy-momentum four-vectors of the final state particles. We demonstrate the proof-of-concept of our White Box AI approach using a Generative Adversarial Network (GAN) which learns from a...

6. How to GAN Event Unweighting

Mr Mathias Backes (Uni Heidelberg)

07/07/2021, 17:00

Simulation and Generative Models

Event generation with neural networks has seen significant progress recently. The big open question is still how such new methods will accelerate LHC simulations to the level required by upcoming LHC runs. We target a known bottleneck of standard simulations and show how their unweighting procedure can be improved by generative networks. This can, potentially, lead to a very significant gain...

20. Jet Identification in L1 Trigger at HL-LHC based on DNN implementation on FPGA

Dr Andre Sznajder (UERJ (Brazil))

07/07/2021, 17:00

Regression, Calibration, and Fast Inference

We investigate the possibility of using Deep Learning algorithms for jet identification in the L1 trigger at HL-LHC. We perform a survey of architectures (MLP, CNN, Graph Networks) and benchmark their performance and resource consumption on FPGAs using a QKeras+hls4ml compression-aware training procedure. We use the HLS4ML jet dataset to compare the results obtained in this study to previous...

16. OnlineFlow: Trigger Free Analysis Using Online Learned Generative Models

Sascha Daniel Diefenbacher (Hamburg University (DE))

07/07/2021, 17:20

Regression, Calibration, and Fast Inference

The high collision rates at the Large Hadron Collider (LHC) make it impossible to store every single observed interaction. For this reason, only a small subset that passes so-called triggers — which select potentially interesting events — are saved while the remainder is discarded. This makes it difficult to perform searches in regions that are usually ignored by trigger setups, for example at...

78. Sparse Data Generation with Convolutional VAE

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

07/07/2021, 17:20

Simulation and Generative Models

A key aspect for the study of particle collisions is the comparison of the experiments data with those resulting from computer simulations, mainly obtained using Monte Carlo-based generators. However the amount of data required in simulations makes this task very time consuming. One approach to avoid this issue is by using machine learning techniques to speed up this process.
In this work,...

97. Super-Resolution for QCD and Top Jets

Lukas Blecher (Universität Heidelberg)

07/07/2021, 17:40

Simulation and Generative Models

QCD-jets at the LHC are described by simple physics principles. We show how super-resolution generative networks can learn the underlying structures and use them to improve the resolution of jet images. We test this approach on massless QCD-jets and on fat top-jets and find that the network reproduces their main features even without training on pure samples. In addition, we show how a slim...

58. Implementation of Jupyter Notebooks into The Reproducible Open Benchmarks for Data Analysis Platform (ROB)

Aaron Wang, Heiko Mueller

07/07/2021, 20:00

Datasets

The Reproducible Open Benchmarks for Data Analysis Platform (ROB) is a platform that allows for the evaluation of different data analysis algorithms in a controlled competition-style format [1]. One example for such a comparison and evaluation of different algorithms is the “The Machine Learning Landscape of Top Taggers” paper, which compiled and compared multiple different top tagger neural...

66. Shared Data and Algorithms for Deep Learning in Fundamental Physics

William Korcari (Hamburg University (DE))

07/07/2021, 20:20

Datasets

We introduce a collection of datasets from fundamental physics research including particle physics, astroparticle physics, hadron, and nuclear physics for supervised machine learning studies. These datasets, containing hadronic top quarks, cosmic air showers, phase transitions in the hadronic matter, and generator-level histories, are combined and made public to simplify future work on...

91. Introduction to Anomaly Detection Challenge

Katya Govorkova (CERN)

07/07/2021, 20:40

Datasets

The data challenge is "anomaly detection @ 40 MHz" for which the biggest concern
is to fit an algorithm in the tight constraints, which are presented in the talk.
Considering as a benchmark an inclusive data stream, which has been pre-filtered
by requiring the presence of one lepton, we discuss different possible strategies
to detect new physics events as anomalies. The main goal of...

99. Calorimeter Simulation Challenge Proposal

David Shih (Rutgers University)

07/07/2021, 21:00

Datasets

26. Learning Symmetries and Conserved Quantities of Physical Systems

Sven Krippendorf

08/07/2021, 09:00

Exploring the Latent Structure of Data

This talk is about how we can use ML to identify symmetries (conserved quantities) of physical systems. I report on three different strategies to find symmetries:
1) By examining the embedding a (deep) neural network adapts on a simple supervised task (2003.13679).
2) By imposing a modification to Hamiltonian Neural Networks such that a coordinate transformation ensures the emergence of...

7. Bump Hunting in Latent Space

Aleks Smolkovic (Jozef Stefan Institute Ljubljana)

08/07/2021, 09:20

Exploring the Latent Structure of Data

Unsupervised anomaly detection could be crucial in future analyses searching for rare phenomena in large datasets, as for example collected at the LHC. To this end, we introduce a physics inspired variational autoencoder (VAE) architecture which performs competitively and robustly on the LHC Olympics Machine Learning Challenge datasets. We demonstrate how embedding some physical observables...

50. Symmetry Discovery with Deep Learning

Krish Desai (University of California, Berkeley)

08/07/2021, 09:40

Exploring the Latent Structure of Data

Symmetries are a fundamental property of functions applied to datasets. A key function for any dataset is the probability density, and the corresponding symmetries are often referred to as the symmetries of the dataset itself. We provide a rigorous statistical notion of symmetry for a dataset, which involves reference datasets that we call ...

21. The Blessing of Dimensionality: Dimensionality Estimation for Event Clustering

Malte Jacobsen (Hamburg University (DE))

08/07/2021, 10:00

Exploring the Latent Structure of Data

Fundamental laws of physics introduce specific topological features in the phase-space of n-body processes in collider events. We introduce a new analysis approach relying on analyzing such global topological properties of the manifold over the distribution of events. One specific property of potential interest is the dimensionality of the phase space. It can, for example, be used for...

5. Detecting hidden patterns in jet substructure with probabilistic models

Darius Faroughy (University of Zurich)

08/07/2021, 10:20

Exploring the Latent Structure of Data

We build a simple probabilistic model for collider events represented by a pattern of points in a space of high-level observables. The model is based on three assumptions for the point data: the measurements in individual events are discrete, exchangeable, and generated from a mixture of latent distributions, or 'themes'. The result is a mixed-membership model known as Latent Dirichlet...

81. Attention and Dynamic Graph Convolution Neural Network in the context of classifying ttH(bb) vs. tt(bb) in the semi-leptonic top quark pair decay channel

Christina Reissel (ETH Zurich (CH))

08/07/2021, 10:40

Exploring the Latent Structure of Data

Deep neural networks (DNNs) are essential tools in particle physics targeting various use cases ranging from reconstruction of particles up to event classification and anomaly detection. Whereas DNNs for event classification are primarily trained on quantities deduced from the kinematic properties of the particles in the final state (high-level observables), we present an alternative approach...

9. Better latent spaces for better autoencoders

Dr Barry Dillon (University of Heidelberg)

08/07/2021, 11:00

Exploring the Latent Structure of Data

Autoencoders as tools behind anomaly searches at the LHC have the structural problem that they only work in one direction, extracting jets with higher complexity but not the other way around. To address this, we derive classifiers from the latent space of (variational) autoencoders, specifically in Gaussian mixture and Dirichlet latent spaces. In particular, the Dirichlet setup solves the...

18. Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network

Erik Buhmann (Hamburg University (DE))

08/07/2021, 11:20

Exploring the Latent Structure of Data

Given the increasing data collection capabilities and limited computing resources of future collider experiments, interest in using generative neural networks for the fast simulation of collider events is growing. In our previous study, the Bounded Information Bottleneck Autoencoder (BIB-AE) architecture for generating photon showers in a high-granularity calorimeter showed a high accuracy...

51. Jet Topology

Sijun Xu (Hong Kong University of Science and Technology)

08/07/2021, 11:40

Exploring the Latent Structure of Data

We introduce persistent Betti numbers to characterize topological structure of jets. These topological invariants measure multiplicity and connectivity of jet branches at a given scale threshold, while their persistence records evolution of each topological feature as this threshold varies. With this knowledge, in particular, we are able to reconstruct branch phylogenetic tree of each jet....

63. Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes

Manuel Haußmann (Universität Heidelberg)

08/07/2021, 14:00

Interpretability, Robustness, and Uncertainties

Neural Stochastic Differential Equations model a dynamical environment with neural nets assigned to their drift and diffusion terms. The high expressive power of their nonlinearity comes at the expense of instability in the identification of the large set of free parameters. This worok presents a recipe to improve the prediction accuracy of such models in three steps: i) accounting for...

13. Uncertainties Associated with GAN Generated Datasets

Prasanth Shyamsundar (Fermi National Accelerator Laboratory)

08/07/2021, 14:40

Interpretability, Robustness, and Uncertainties

Recently, Generative Adversarial Networks (GANs) trained on samples of traditionally simulated collider events have been proposed as a way of generating larger simulated datasets at a reduced computational cost. In this talk we will present an argument cautioning against the usage of this method to meet the simulation requirements of an experiment, namely that data generated by a GAN cannot...

94. Generative Networks with Uncertainties

Michel Luchmann, Tilman Plehn

08/07/2021, 15:00

Interpretability, Robustness, and Uncertainties

We show how Bayesian neural networks can be used to estimate uncertainties associated with regression, classification, and now also generative networks. For generative INNs, the combination of the learned density and uncertainty maps also provide insights into how these networks learn. These results show that criticizing the use of neural networks in LHC physics as black boxes is a...

25. Uncertainty Aware Learning for High Energy Physics

Aishik Ghosh (University of California Irvine (US))

08/07/2021, 15:20

Interpretability, Robustness, and Uncertainties

Machine learning techniques are becoming an integral component of data analysis in High Energy Physics (HEP). These 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...

15. Amplifying Statistics with Generative Models

Sebastian Bieringer

08/07/2021, 15:40

Interpretability, Robustness, and Uncertainties

Monte Carlo simulations are a vital part of modern particle physics. However classical approaches to these simulations require a vast amount of computational resources. Generative Machine Learning models offer a chance to reduce this strain on computing capabilities by allowing us to generate simulated data at a significantly greater speed. The applicability of such generative models has been...

61. Safety of Quark/Gluon Jet Classification

Alexis Romero

08/07/2021, 16:00

Interpretability, Robustness, and Uncertainties

The classification of jets as quark- versus gluon-initiated is an important yet challenging task in the analysis of data from high-energy particle collisions and in the search for physics beyond the Standard Model. The recent integration of deep neural networks operating on low-level detector information has resulted in significant improvements in the classification power of quark/gluon jet...

43. Thoughts on the expressive power and inductive bias of DeepSets and Tree-Based models

Kyle Stuart Cranmer (New York University (US))

08/07/2021, 16:20

Interpretability, Robustness, and Uncertainties

Nearly five years ago we introduced tree-based recursive NN models for jet physics, which intuitively reflected the sequence of 1-to-2 splittings found in a parton shower. Subsequently, tree-based models like JUNIPR were developed as (probabilistic) generative models that could be used for classification and reweighing. One result that somewhat undermined the narrative of the connection...

10. Explainable AI for ML Jet Taggers

Christine Angela McLean (SUNY Buffalo)

08/07/2021, 16:40

Interpretability, Robustness, and Uncertainties

A framework is presented to extract and understand decision-making information from a deep neural network classifier of jet substructure tagging techniques. The general method studied is to provide expert variables that augment inputs (“eXpert AUGmented” variables, or XAUG variables), then apply layerwise relevance propagation (LRP) to networks that have been provided XAUG variables and those...

100. Bayesian Inference in for Four Tops at the LHC

Ezequiel Alvarez de los Alvarez de San Luis

08/07/2021, 17:00

Interpretability, Robustness, and Uncertainties

Four-tops (and its backgrounds) is very hard to model at the LHC, it represents a unique window for detecting top-philic NP, and its current measurements have some tension with theory and predictions. We find that simple, clean and powerful Bayesian Inference can be applied on the data to infer signal and background true distributions. We propose that these results could be used in a novel...

2. Spectral Clustering for Jet Formation

Henry Day-Hall (University of Southampton)

08/07/2021, 17:20

Interpretability, Robustness, and Uncertainties

Machine learning (ML) is pushing through boundaries in computational physics.
Jet physics, with it's large and detailed dataset, is particularly well suited.
In this talk I will discuss the application of an unusual ML technique, Spectral Clustering, to jet formation.

Spectral clustering differers from much of ML as it has no "black-box" elements.
Instead, it is based on a simple,...

41. Deep-Learned Event Variables

Doojin Kim (Texas A & M University (US))

08/07/2021, 17:40

Interpretability, Robustness, and Uncertainties

The choice of optimal event variables is crucial for achieving the maximal sensitivity of experimental analyses, and suitable kinematic variables for many well-motivated event topologies have been developed in collider physics. Here we propose a deep-learning-based algorithm to design good event variables that are sensitive to a wide range of the unknown model parameter values. We demonstrate...

93. ML in Cosmological Simulations

Annalisa Pillepich

08/07/2021, 20:00

New Horizons

52. Conditional invertible neural networks to probe cosmic-ray sources

Josina Schulte (RWTH Aachen University)

08/07/2021, 20:40

New Horizons

To obtain information on the still unknown sources of ultra-high-energy cosmic rays (UHECRs), a combined fit of the observed energy spectrum and depths of the shower maximum can be used, which constrains characteristic parameters of the sources. During propagation from the sources to Earth, UHECRs can experience numerous stochastic processes such that no explicit inverse function, which would...

79. Via Machinae

Matthew Buckley (Rutgers University)

08/07/2021, 21:00

New Horizons

I describe a new machine learning algorithm, Via Machinae, to identify cold stellar streams in data from the Gaia telescope. Via Machinae is based on ANODE, a general method that uses conditional density estimation and sideband interpolation to detect local overdensities in the data in a model agnostic way. By applying ANODE to the positions, proper motions, and photometry of stars observed by...

28. Synergies between Quantum Computing and Machine Learning

Michael Spannowsky (University of Durham (GB))

08/07/2021, 21:20

New Horizons

I will give a very brief (and incomplete) review on quantum machine learning techniques and focus then on novel quantum computing approaches for the task of finding a solution to an optimisation problem. I will then give explicit examples how quantum machine learning techniques can be used for classification tasks and to calculate solutions to nonperturbative problems in quantum field theory.

102. Closeout and ML4Jets2022

Ben Nachman (Lawrence Berkeley National Lab. (US)), David Shih (Rutgers University), Tilman Plehn

08/07/2021, 21:45

92. Generative Adversarial Networks for Anomaly Detection at the LHC

Daniel Sun (University of Washington)

BSM

Anomaly detection techniques offer exciting possibilities to significantly extend the search for new physics at the Large Hadron Collider (LHC) in a model-agnostic approach. We study how Generative Adversarial Networks could be used for this purpose, using the LHC Olympics 2020 dataset as an example.

101. ML4Jets2022

David Shih (Rutgers University)

New Horizons