arXiv subjects

Gregor Kasieczka

Publications and source records attributed to Gregor Kasieczka.

90 records · Page 5Linked to original sources

arXiv2021

Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed

Accurate simulation of physical processes is crucial for the success of modern particle physics. However, simulating the development and interaction of particle showers with calorimeter detectors is a time consuming process and drives the computing needs of large experiments at the LHC and future colliders. Recently, generative machine learning models based on deep neural networks have shown promise in speeding up this task by several orders of magnitude. We investigate the use of a new architecture -- the Bounded Information Bottleneck Autoencoder -- for modelling electromagnetic showers in the central region of the Silicon-Tungsten calorimeter of the proposed International Large Detector. Combined with a novel second post-processing network, this approach achieves an accurate simulation of differential distributions including for the first time the shape of the minimum-ionizing-particle peak compared to a full GEANT4 simulation for a high-granularity calorimeter with 27k simulated channels. The results are validated by comparing to established architectures. Our results further strengthen the case of using generative networks for fast simulation and demonstrate that physically relevant differential distributions can be described with high accuracy.

physics.ins-det↗

arXiv2021

The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics

A new paradigm for data-driven, model-agnostic new physics searches at colliders is emerging, and aims to leverage recent breakthroughs in anomaly detection and machine learning. In order to develop and benchmark new anomaly detection methods within this framework, it is essential to have standard datasets. To this end, we have created the LHC Olympics 2020, a community challenge accompanied by a set of simulated collider events. Participants in these Olympics have developed their methods using an R&D dataset and then tested them on black boxes: datasets with an unknown anomaly (or not). This paper will review the LHC Olympics 2020 challenge, including an overview of the competition, a description of methods deployed in the competition, lessons learned from the experience, and implications for data analyses with future datasets as well as future colliders.

hep-ph↗

arXiv2020

Per-Object Systematics using Deep-Learned Calibration

We show how to treat systematic uncertainties using Bayesian deep networks for regression. First, we analyze how these networks separately trace statistical and systematic uncertainties on the momenta of boosted top quarks forming fat jets. Next, we propose a novel calibration procedure by training on labels and their error bars. Again, the network cleanly separates the different uncertainties. As a technical side effect, we show how Bayesian networks can be extended to describe non-Gaussian features.

hep-ph↗

arXiv2020

Invertible Networks or Partons to Detector and Back Again

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 and QCD radiation to a pre-defined hard process, again with a per-event probabilistic interpretation over parton-level phase space.

hep-ph↗

arXiv2020

DisCo Fever: Robust Networks Through Distance Correlation

While deep learning has proven to be extremely successful at supervised classification tasks at the LHC and beyond, for practical applications, raw classification accuracy is often not the only consideration. One crucial issue is the stability of network predictions, either versus changes of individual features of the input data, or against systematic perturbations. We present a new method based on a novel application of "distance correlation" (DisCo), a measure quantifying non-linear correlations, that achieves equal performance to state-of-the-art adversarial decorrelation networks but is much simpler and more stable to train. To demonstrate the effectiveness of our method, we carefully recast a recent ATLAS study of decorrelation methods as applied to boosted, hadronic W-tagging. We also show the feasibility of DisCo regularization for more powerful convolutional neural networks, as well as for the problem of hadronic top tagging.

hep-ph↗

arXiv2020

Towards Machine Learning Analytics for Jet Substructure

The past few years have seen a rapid development of machine-learning algorithms. While surely augmenting performance, these complex tools are often treated as black-boxes and may impair our understanding of the physical processes under study. The aim of this paper is to move a first step into the direction of applying expert-knowledge in particle physics to calculate the optimal decision function and test whether it is achieved by standard training, thus making the aforementioned black-box more transparent. In particular, we consider the binary classification problem of discriminating quark-initiated jets from gluon-initiated ones. We construct a new version of the widely used N-subjettiness, which features a simpler theoretical behaviour than the original one, while maintaining, if not exceeding, the discrimination power. We input these new observables to the simplest possible neural network, i.e. the one made by a single neuron, or perceptron, and we analytically study the network behaviour at leading logarithmic accuracy. We are able to determine under which circumstances the perceptron achieves optimal performance. We also compare our analytic findings to an actual implementation of a perceptron and to a more realistic neural network and find very good agreement.

hep-ph↗

arXiv2020

DCTRGAN: Improving the Precision of Generative Models with Reweighting

Significant advances in deep learning have led to more widely used and precise neural network-based generative models such as Generative Adversarial Networks (GANs). We introduce a post-hoc correction to deep generative models to further improve their fidelity, based on the Deep neural networks using the Classification for Tuning and Reweighting (DCTR) protocol. The correction takes the form of a reweighting function that can be applied to generated examples when making predictions from the simulation. We illustrate this approach using GANs trained on standard multimodal probability densities as well as calorimeter simulations from high energy physics. We show that the weighted GAN examples significantly improve the accuracy of the generated samples without a large loss in statistical power. This approach could be applied to any generative model and is a promising refinement method for high energy physics applications and beyond.

hep-ph↗

arXiv2020

ABCDisCo: Automating the ABCD Method with Machine Learning

The ABCD method is one of the most widely used data-driven background estimation techniques in high energy physics. Cuts on two statistically-independent classifiers separate signal and background into four regions, so that background in the signal region can be estimated simply using the other three control regions. Typically, the independent classifiers are chosen "by hand" to be intuitive and physically motivated variables. Here, we explore the possibility of automating the design of one or both of these classifiers using machine learning. We show how to use state-of-the-art decorrelation methods to construct powerful yet independent discriminators. Along the way, we uncover a previously unappreciated aspect of the ABCD method: its accuracy hinges on having low signal contamination in control regions not just overall, but relative to the signal fraction in the signal region. We demonstrate the method with three examples: a simple model consisting of three-dimensional Gaussians; boosted hadronic top jet tagging; and a recasted search for paired dijet resonances. In all cases, automating the ABCD method with machine learning significantly improves performance in terms of ABCD closure, background rejection and signal contamination.

hep-ph↗

arXiv2020

How to GAN away Detector Effects

LHC analyses directly comparing data and simulated events bear the danger of using first-principle predictions only as a black-box part of event simulation. We show how simulations, for instance, of detector effects can instead be inverted using generative networks. This allows us to reconstruct parton level information from measured events. Our results illustrate how, in general, fully conditional generative networks can statistically invert Monte Carlo simulations. As a technical by-product we show how a maximum mean discrepancy loss can be staggered or cooled.

hep-ph↗

arXiv2019

CapsNets Continuing the Convolutional Quest

Capsule networks are ideal tools to combine event-level and subjet information at the LHC. After benchmarking our capsule network against standard convolutional networks, we show how multi-class capsules extract a resonance decaying to top quarks from both, QCD di-jet and the top continuum backgrounds. We then show how its results can be easily interpreted. Finally, we use associated top-Higgs production to demonstrate that capsule networks can work on overlaying images to go beyond calorimeter information.

hep-ph↗

arXiv2019

Deep-Learning Jets with Uncertainties and More

Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers. We show how they capture statistical uncertainties from finite training samples, systematics related to the jet energy scale, and stability issues through pile-up. Altogether, Bayesian networks offer many new handles to understand and control deep learning at the LHC without introducing a visible prior effect and without compromising the network performance.

hep-ph↗

arXiv2019

Quark-Gluon Tagging: Machine Learning vs Detector

Distinguishing quarks from gluons based on low-level detector output is one of the most challenging applications of multi-variate and machine learning techniques at the LHC. We first show the performance of our 4-vector-based LoLa tagger without and after considering detector effects. We then discuss two benchmark applications, mono-jet searches with a gluon-rich signal and di-jet resonances with a quark-rich signal. In both cases an immediate benefit compared to the standard event-level analysis exists.

hep-ph↗

arXiv2019

QCD or What?

Autoencoder networks, trained only on QCD jets, can be used to search for anomalies in jet-substructure. We show how, based either on images or on 4-vectors, they identify jets from decays of arbitrary heavy resonances. To control the backgrounds and the underlying systematics we can de-correlate the jet mass using an adversarial network. Such an adversarial autoencoder allows for a general and at the same time easily controllable search for new physics. Ideally, it can be trained and applied to data in the same phase space region, allowing us to efficiently search for new physics using un-supervised learning.

hep-ph↗

arXiv2018

Deep-learned Top Tagging with a Lorentz Layer

We introduce a new and highly efficient tagger for hadronically decaying top quarks, based on a deep neural network working with Lorentz vectors and the Minkowski metric. With its novel machine learning setup and architecture it allows us to identify boosted top quarks not only from calorimeter towers, but also including tracking information. We show how the performance of our tagger compares with QCD-inspired and image-recognition approaches and find that it significantly increases the performance for strongly boosted top quarks.

hep-ph↗

arXiv2018

Boosted Top Tagging Method Overview

We briefly review common tools and methods to identify boosted, hadronically decaying top quarks at the LHC experiments. This includes generic jet substructure variables, specific top identification algorithms, and recent developments in deep learning techniques.

hep-ph↗

arXiv2017

Deep-learning Top Taggers or The End of QCD?

Machine learning based on convolutional neural networks can be used to study jet images from the LHC. Top tagging in fat jets offers a well-defined framework to establish our DeepTop approach and compare its performance to QCD-based top taggers. We first optimize a network architecture to identify top quarks in Monte Carlo simulations of the Standard Model production channel. Using standard fat jets we then compare its performance to a multivariate QCD-based top tagger. We find that both approaches lead to comparable performance, establishing convolutional networks as a promising new approach for multivariate hypothesis-based top tagging.

hep-ph↗

arXiv2015

Resonance Searches with an Updated Top Tagger

The performance of top taggers, for example in resonance searches, can be significantly enhanced through an increased set of variables, with a special focus on final-state radiation. We study the production and the decay of a heavy gauge boson in the upcoming LHC run. For constant signal efficiency, the multivariate analysis achieves an increased background rejection by up to a factor 30 compared to our previous tagger. Based on this study and the documentation in the Appendix we release a new HEPTopTagger2 for the upcoming LHC run. It now includes an optimal choice of the size of the fat jet, N-subjettiness, and different modes of Qjets.

hep-ph↗

arXiv2014

Benchmarking an Even Better HEPTopTagger

Top taggers are established analysis tools to reconstruct boosted hadronically decaying top quarks for example in searches for heavy resonances. We first present a dedicated study of signal efficiency versus background rejection, allowing for an improved choice of working points. Next, we determine to what degree our mass drop selection can be improved by systematically including angular correlations between the decay subjets. Finally, we extend the reach of the top tagger to transverse momenta below the top mass. This momentum range will be crucial in searches for the associated production of a Higgs boson with top quarks.

hep-ph↗