Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInterpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
232
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Classification of jets with deep learning has gained significant attention in recent times. However, the performance of deep neural networks is often achieved at the cost of interpretability. Here we propose an interpretable network trained on the jet spectrum $S_{2}(R)$ which is a two-point correlation function of the jet constituents. The spectrum can be derived from a functional Taylor series of an arbitrary jet classifier function of energy flows. An interpretable network can be obtained by truncating the series. The intermediate feature of the network is an infrared and collinear safe C-correlator which allows us to estimate the importance of a $S_{2}(R)$ deposit at an angular scale R in the classification. The performance of the architecture is comparable to that of a convolutional neural network (CNN) trained on jet images, although the number of inputs and complexity of architecture is significantly simpler than the CNN classifier. We consider two examples: one is the classification of two-prong jets which differ in color charge of the mother particle, and the other is a comparison between Pythia 8 and Herwig 7 generated jets.
rate research
Read More
Observables which distinguish boosted topologies from QCD jets are playing an increasingly important role at the Large Hadron Collider (LHC). These observables are often used in conjunction with jet grooming algorithms, which reduce contamination from both theoretical and experimental sources. In this paper we derive factorization formulae for groomed multi-prong substructure observables, focusing in particular on the groomed $D_2$ observable, which is used to identify boosted hadronic decays of electroweak bosons at the LHC. Our factorization formulae allow systematically improvable calculations of the perturbative $D_2$ distribution and the resummation of logarithmically enhanced terms in all regions of phase space using renormalization group evolution. They include a novel factorization for the production of a soft subjet in the presence of a grooming algorithm, in which clustering effects enter directly into the hard matching. We use these factorization formulae to draw robust conclusions of experimental relevance regarding the universality of the $D_2$ distribution in both $e^+e^-$ and $pp$ collisions. In particular, we show that the only process dependence is carried by the relative quark vs. gluon jet fraction in the sample, no non-global logarithms from event-wide correlations are present in the distribution, hadronization corrections are controlled by the perturbative mass of the jet, and all global color correlations are completely removed by grooming, making groomed $D_2$ a theoretically clean QCD observable even in the LHC environment. We compute all ingredients to one-loop accuracy, and present numerical results at next-to-leading logarithmic accuracy for $e^+e^-$ collisions, comparing with parton shower Monte Carlo simulations. Results for $pp$ collisions, as relevant for phenomenology at the LHC, are presented in a companion paper.
We introduce a jet tagger based on a neural network analyzing the Minkowski Functionals (MFs) of pixellated jet images. The MFs are geometric measures of binary images, and they can be regarded as a generalization of the particle multiplicity, which is an important quantity in jet tagging. Their changes by dilation encode the jet constituents geometric structures that appear at various angular scales. We explicitly show that this analysis using the MFs together with mathematical morphology can be considered a constrained convolutional neural network (CNN). Conversely, CNN could model the MFs in a certain limit, and we show their correlation in the example of tagging semi-visible jets emerging from the strong interaction of a hidden valley scenario. The MFs are independent of the IRC-safe observables commonly used in jet physics. We combine this morphological analysis with an IRC-safe relation network which models two-point energy correlations. While the resulting network uses constrained input parameters, it shows comparable dark jet and top jet tagging performances to the CNN. The architecture has significant computational advantages when the available data is limited. We show that its tagging performance is much better than that of the CNN with a small number of training samples. We also qualitatively discuss their parton-shower model dependency. The results suggest that the MFs can be an efficient parameterization of the IRC-unsafe feature space of jets.
We study the lepton-jet correlation in deep inelastic scattering. We perform one-loop calculations for the spin averaged and transverse spin dependent differential cross sections depending on the total transverse momentum of the final state lepton and the jet. The transverse momentum dependent (TMD) factorization formalism is applied to describe the relevant observables. To show the physics reach of this process, we perform a phenomenological study for HERA kinematics and comment on an ongoing analysis of experimental data. In addition, we highlight the potential of this process to constrain small-$x$ dynamics.
Jet flavour classification is of paramount importance for a broad range of applications in modern-day high-energy-physics experiments, particularly at the LHC. In this paper we propose a novel architecture for this task that exploits modern deep learning techniques. This new model, called DeepJet, overcomes the limitations in input size that affected previous approaches. As a result, the heavy flavour classification performance improves, and the model is extended to also perform quark-gluon tagging.
Deep learning techniques have the power to identify the degree of modification of high energy jets traversing deconfined QCD matter on a jet-by-jet basis. Such knowledge allows us to study jets based on their initial, rather than final energy. We show how this new technique provides unique access to the genuine configuration profile of jets over the transverse plane of the nuclear collision, both with respect to their production point and their orientation. Effectively removing the selection biases induced by final-state interactions, one can in this way analyse the potential azimuthal anisotropies of jet production associated to initial-state effects. Additionally, we demonstrate the capability of our new method to locate with remarkable precision the production point of a dijet pair in the nuclear overlap region, in what constitutes an important step forward towards the long term quest of using jets as tomographic probes of the quark-gluon plasma.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
