Deep learning techniques are currently being investigated for high energy physics experiments, to tackle a wide range of problems, with quark and gluon discrimination becoming a benchmark for new algorithms.
One weakness is the traditional reliance on Monte Carlo simulations, which may not be well modelled at the detail required by deep learning algorithms.
The weakly supervised learning paradigm gives an alternate route to classification, by using samples with different quark--gluon proportions instead of fully labeled samples.
The paradigm has, therefore, huge potential for particle physics classification problems as these weakly supervised learning methods can be applied directly to collision data.
In this study, we show that realistically simulated samples of dijet and Z+jet events can be used to discriminate between quark and gluon jets by using weakly supervised learning.
We implement and compare the performance of weakly supervised learning for quark--gluon jet classification using three different machine learning methods: the jet image-based convolutional neural network, the particle-based recurrent neural network and the feature-based boosted decision tree.
Currently, newly developed artificial intelligence techniques, in particular convolutional neural networks, are being investigated for use in data-processing and classification of particle physics collider data. One such challenging task is to distinguish quark-initiated jets from gluon-initiated jets. Following previous work, we treat the jet as an image by pixelizing track information and calorimeter deposits as reconstructed by the detector. We test the deep learning paradigm by training several recently developed, state-of-the-art convolutional neural networks on the quark-gluon discrimina…
We study the impact of including quark- and gluon-initiated jet discrimination in the search for strongly interacting supersymmetric particles at the LHC. Taking the example of gluino pair production, considerable improvement is observed in the LHC search reach on including the jet substructure observables to the standard kinematic variables within a multivariate analysis. In particular, quark and gluon jet separation has higher impact in the region of intermediate mass-gap between the gluino and the lightest neutralino, as the difference between the signal and the standard model background ki…
Understanding jets initiated by quarks and gluons is of fundamental importance in collider physics. Efficient and robust techniques for quark versus gluon jet discrimination have consequences for new physics searches, precision $α_s$ studies, parton distribution function extractions, and many other applications. Numerous machine learning analyses have attacked the problem, demonstrating that good performance can be obtained but generally not providing an understanding for what properties of the jets are responsible for that separation power. In this paper, we provide an extensive and detailed …
We estimate the number of quark jets in QCD multi-jet final states at hadron colliders. In the estimation, we develop the calculation of jet rates into that of quark jet rates. From the calculation, we estimate the improvement on the signal-to-background ratio for a signal semi-analytically by applying quark/gluon discrimination, where the signal predicts many quark jets. We introduce a variable related to jet flavors in multi-jet final states and propose a data-driven method using the variable to reduce systematic uncertainties of analysis results. As the same with the semi-analytical result,…
Predictions for our ability to distinguish quark and gluon jets vary by more than a factor of two between different parton showers. We study this problem using analytic resummed predictions for the thrust event shape up to NNLL' using $e^+e^- \to Z \to q \bar q$ and $e^+e^- \to H \to gg$ as proxies for quark and gluon jets. We account for hadronization effects through a nonperturbative shape function, and include an estimate of both perturbative and hadronization uncertainties. In contrast to previous studies, we find reasonable agreement between our results and predictions from both Pythia an…
Charged track multiplicity is among the most powerful observables for discriminating quark- from gluon-initiated jets. Despite its utility, it is not infrared and collinear (IRC) safe, so perturbative calculations are limited to studying the energy evolution of multiplicity moments. While IRC-safe observables, like jet mass, are perturbatively calculable, their distributions often exhibit Casimir scaling, such that their quark/gluon discrimination power is limited by the ratio of quark to gluon color factors. In this paper, we introduce new IRC-safe counting observables whose discrimination pe…
We show that in studies of light quark- and gluon-initiated jet discrimination, it is important to include the information on softer reconstructed jets (associated jets) around a primary hard jet. This is particularly relevant while adopting a small radius parameter for reconstructing hadronic jets. The probability of having an associated jet as a function of the primary jet transverse momentum ($p_T$) and radius, the minimum associated jet $p_T$ and the association radius is computed upto next-to-double logarithmic accuracy (NDLA), and the predictions are compared with results from Herwig++, …
Discriminating quark jets from gluon jets is an important but challenging problem in jet substructure. In this paper, we use the concept of mutual information to illuminate the physics of quark/gluon tagging. Ideal quark/gluon separation requires only one bit of truth information, so even if two discriminant variables are largely uncorrelated, they can still share the same "truth overlap". Mutual information can be used to diagnose such situations, and thus determine which discriminant variables are redundant and which can be combined to improve performance. Using both parton showers and analy…
JUNIPR is an approach to unsupervised learning in particle physics that scaffolds a probabilistic model for jets around their representation as binary trees. Separate JUNIPR models can be learned for different event or jet types, then compared and explored for physical insight. The relative probabilities can also be used for discrimination. In this paper, we show how the training of the separate models can be refined in the context of classification to optimize discrimination power. We refer to this refined approach as Binary JUNIPR. Binary JUNIPR achieves state-of-the-art performance for quar…
Jet tagging is a crucial classification task in high energy physics. Recently the performance of jet tagging has been significantly improved by the application of deep learning techniques. In this study, we introduce a new architecture for jet tagging: the Particle Dual Attention Transformer (P-DAT). This novel transformer architecture stands out by concurrently capturing both global and local information, while maintaining computational efficiency. Regarding the self attention mechanism, we have extended the established attention mechanism between particles to encompass the attention mechanis…
Artificial intelligence offers the potential to automate challenging data-processing tasks in collider physics. To establish its prospects, we explore to what extent deep learning with convolutional neural networks can discriminate quark and gluon jets better than observables designed by physicists. Our approach builds upon the paradigm that a jet can be treated as an image, with intensity given by the local calorimeter deposits. We supplement this construction by adding color to the images, with red, green and blue intensities given by the transverse momentum in charged particles, transverse …
Since the machine learning techniques are improving rapidly, it has been shown that the image recognition techniques in deep neural networks can be used to detect jet substructure. And it turns out that deep neural networks can match or outperform traditional approach of expert features. However, there are disadvantages such as sparseness of jet images. Based on the natural tree-like structure of jet sequential clustering, the recursive neural networks (RecNNs), which embed jet clustering history recursively as in natural language processing, have a better behavior when confronted with these p…
We present a comparison of data of lepton angular distributions of Drell-Yan/$Z$ production with the fixed-order pQCD calculations by which the baseline of pQCD effects is illustrated. As for the $Z$ production, we predict that $A_0$ and $A_2$ for $Z$ plus single gluon-jet events are very different from that of $Z$ plus single quark-jet events, allowing a new experimental tool for checking various algorithms which attempt to discriminate quark jets from gluon jets. Using an intuitive geometric approach, we show that the violation of the Lam-Tung relation, appearing at large transverse-momentum…
High precision data of lepton angular distributions in inclusive $Z$ boson production, reported by the CMS and ATLAS Collaborations, showed pronounced transverse momentum ($q_T$) dependencies of the $A_0$ and $A_2$ coefficients. Violation of the Lam-Tung relation, $A_0 = A_2$, was also found. An intuitive understanding of these results can be obtained from a geometric approach. We predict that $A_0$ and $A_2$ for $Z$ plus single gluon-jet events are very different from that of $Z$ plus single quark-jet events, allowing a new experimental tool for checking various algorithms which attempt to di…
The transverse momentum broadening coefficient $\hat{q}$ receives both soft, classical and radiative, quantum corrections. The former are responsible for a large O(g) correction, whereas the latter enter at relative order $α_s$, but are enhanced by a double logarithm of the length of the medium over the thermal wavelength. We analyze radiative corrections for a weakly-coupled quark-gluon plasma. We find that a thermal population of dynamical gluons changes the boundaries and reduces the size of the double-logarithmic phase space. It also provides new subdominant logarithmic corrections. We als…
New jet observables are defined which characterize both fractal and scale-dependent contributions to the distribution of hadrons in a jet. These infrared safe observables, named Extended Fractal Observables (EFOs), have been applied to quark-gluon discrimination to demonstrate their potential utility. The EFOs are found to be individually discriminating and only weakly correlated to variables used in existing discriminators. Consequently, their inclusion improves discriminator performance, as here demonstrated with particle level simulation from the parton shower.
We study the polarization and dispersion properties of gluons moving within a weakly magnetized background at one-loop order. To this end, we show two alternative derivations of the charged fermion propagator in the weak field expansion and use this expression to compute the lowest order magnetic field correction to the gluon polarization tensor. We explicitly show that, in spite of its cumbersome appearance, the gluon polarization tensor is transverse as required by gauge invariance. We also show that none of the three polarization modes develops a magnetic mass and that gluons propagate alon…
Jet substructure observables, designed to identify specific features within jets, play an essential role at the Large Hadron Collider (LHC), both for searching for signals beyond the Standard Model and for testing QCD in extreme phase space regions. In this paper, we systematically study the structure of infrared and collinear safe substructure observables, defining a generalization of the energy correlation functions to probe $n$-particle correlations within a jet. These generalized correlators provide a flexible basis for constructing new substructure observables optimized for specific purpo…
Heavy Quarkonium in a weakly-coupled quark-gluon plasma below the melting temperature
我们计算了一个夸克-胶子等离子体中的重夸克偶素能级和衰变宽度，该等离子体的温度T和屏蔽质量m_D满足m α_s >> T >> m α_s^2>> m_D（m是重夸克质量），m α_s^5阶。我们首先顺序地积分出尺度m、m α_s和T，然后，我们使用区域积分技术在所得到的有效理论中进行计算。确定了一个共线区域，该区域以该顺序起作用。我们还讨论了我们的结果对重离子碰撞中重夸克偶素抑制的影响。
By measuring the substructure of a jet, one can assign it a "quark" or "gluon" tag. In the eikonal (double-logarithmic) limit, quark/gluon discrimination is determined solely by the color factor of the initiating parton (C_F versus C_A). In this paper, we confront the challenges faced when going beyond this leading-order understanding, using both parton-shower generators and first-principles calculations to assess the impact of higher-order perturbative and nonperturbative physics. Working in the idealized context of electron-positron collisions, where one can define a proxy for quark and gluo…
Previous studies have demonstrated the utility and applicability of machine learning techniques to jet physics. In this paper, we construct new observables for the discrimination of jets from different originating particles exclusively from information identified by the machine. The approach we propose is to first organize information in the jet by resolved phase space and determine the effective $N$-body phase space at which discrimination power saturates. This then allows for the construction of a discrimination observable from the $N$-body phase space coordinates. A general form of this obs…
Energy-loss studies of hard particle probes produced in heavy ion collisions have often been used to get information on the interactions within the medium of a quark-gluon plasma (QGP). However, with the study of in-medium energy-loss of individual particles alone, it remains still ambiguous, whether the occured decrease in particle energy is caused by predominantly radiative or collisional energy-loss mechanisms. Focusing on the in-medium energy-loss of hard jet-partons, we propose additional studies of the angular jet-structure as a means to further constrain the energy-loss mechanisms.
Quantum Rationale-Aware Graph Contrastive Learning for Jet Discrimination
University of Southern California（南加州大学）；Jahangirnagar University（贾哈吉尔纳加尔大学）；American International University-Bangladesh（孟加拉国美国国际大学）；Techno International New Town（技术国际新镇）；Khalifa University（卡利法大学）
At proposed future hadron colliders and in the coming years at the LHC, top quarks will be produced at genuinely multi-TeV energies. Top-tagging at such high energies forces us to confront several new issues in terms of detector capabilities and jet physics. Here, we explore these issues in the context of some simple JHU/CMS-type declustering algorithms and the N-subjettiness jet-shape variable tau_32. We first highlight the complementarity between the two tagging approaches at particle-level with respect to discriminating top-jets against gluons and quarks, using multivariate optimization sca…
We introduce a new jet observable {\em zest} defined on exclusively constructed jets and study its potential to discriminate jets originated from Standard Model heavy particles like $W,~Z$ bosons and top quark from gluon initiated jets. Zest exhibits properties such as boost invariance, stability against global color exchange among partons, and inclusion or exclusion of a few soft particles in the jet. We also observe that for gluon jets, zest distribution is mostly insensitive to the jet mass. These properties make zest a suitable candidate for vetoing gluon jets at the colliders. Zest when u…
These are lecture notes presented at the 2017 CTEQ Summer School at the University of Pittsburgh and the 2018 CTEQ Summer School at the University of Puerto Rico, Mayaguez. The title is a reference to hep-th/0309149 and introduces perturbative QCD and its application to jet substructure from a bottom-up perspective based on the approximation of QCD as a weakly-coupled, conformal field theory. Using this approach, a simple derivation of the Sudakov form factor with soft gluon emission modeled as a Poisson process is presented. Topics of the identification and discrimination of quark- versus glu…
We propose a modified definition of the jet charge, the "dynamic jet charge", where the constant jet momentum fraction weighting parameter, $κ$, in the standard jet charge definition is generalized to be a function of a dynamical property of the jet or the individual jet constituents. The dynamic jet charge can complement analyses based on the standard definition and give improved discrimination between quark and gluon initiated jets and between jets initiated by different quark flavors. We focus on the specific scenario where each hadron in the jet contributes to the dynamic jet charge with a…
We present a computation, within weakly-coupled thermal QCD, of the production rate of low invariant mass ($M^2 \sim g^2 T^2$) dileptons, at next-to-leading order (NLO) in the coupling (which is $O(g^3 e^2 T^2)$). This involves extending the NLO calculation of the photon rate which we recently presented to the case of small nonzero photon invariant mass. Numerical results are discussed and tabulated forms and code are provided for inclusion in hydrodynamical models. We find that NLO corrections can increase the dilepton rate by up to 30-40% relative to leading order. We find that the electroma…
We present an extension to next-to-leading order in the strong coupling constant $g$ of the AMY effective kinetic approach to the energy loss of high momentum particles in the quark-gluon plasma. At leading order, the transport of jet-like particles is determined by elastic scattering with the thermal constituents, and by inelastic collinear splittings induced by the medium. We reorganize this description into collinear splittings, high-momentum-transfer scatterings, drag and diffusion, and particle conversions (momentum-preserving identity-changing processes). We show that this reorganized de…
In the early stages of heavy-ion collisions, the hot QCD matter expands more longitudinally than transversely. This imbalance causes the system to become rapidly colder in the longitudinal direction and a local momentum anisotropy appears. In this paper, we study the heavy-quarkonium spectrum in the presence of a small plasma anisotropy. We work in the framework of pNRQCD at finite temperature. We inspect arrangements of non-relativistic and thermal scales complementary to those considered in the literature. In particular, we consider temperatures larger and Debye masses smaller than the bindi…
Jet identification is one of the fields in high energy physics that machine learning has begun to make an impact. More often than not, convolutional neural networks are used to classify jet images with the benefit that essentially no physics input is required. Inspired by a recent work by Datta and Larkoski, we study the classification of quark/gluon-initiated jets based on fully-connected neural networks (FNNs), where expert-designed physical variables are taken as input. FNNs are applied in two ways: trained separately on various narrow jet transverse momentum $p_{TJ}$ bins; trained on a wid…
We study the phenomenon of jet quenching utilizing quark and gluon jet substructures as independent probes of heavy ion collisions. We exploit jet and subjet features to highlight differences between quark and gluon jets in vacuum and in a medium with the jet-quenching model implemented in JEWEL. We begin with a physics-motivated, multivariate analysis of jet substructure observables including the jet mass, the radial moments, the $p_T^D$ and the pixel multiplicity. In comparison, we employ state-of-the-art image-recognition techniques by training a deep convolutional neutral network on jet im…
Plasmons of quark-gluon plasma - gluon collective modes - are systematically studied. The plasma is, in general, non-equilibrium but homogeneous. We consider anisotropic momentum distributions of plasma constituents which are obtained from the isotropic one by stretching or squeezing in one direction. This leads to prolate or oblate distributions, respectively. We study all possible degrees of one dimensional deformation from the extremely prolate case, when the momentum distribution is infinitely elongated in one direction, to the extremely oblate distribution, which is infinitely squeezed in…
Whether quark- and gluon-initiated jets are modified differently by the quark-gluon plasma produced in heavy-ion collisions is a long-standing question that has thus far eluded a definitive experimental answer. A crucial complication for quark-gluon discrimination in both proton-proton and heavy-ion collisions is that all measurements necessarily average over the (unknown) quark-gluon composition of a jet sample. In the heavy-ion context, the simultaneous modification of both the fractions and substructure of quark and gluon jets by the quark-gluon plasma further obscures the interpretation. H…
We present a study of the relative energy loss of quark and gluon jets that traverse a weakly-coupled medium. The study is carried out with the jet quenching Monte-Carlo event generator JEWEL which has been validated for a large set of jet observables. We find that the relative energy loss of quark and gluon jets approaches a constant value at large jet energy and that value is significantly larger (closer to 1) than the single parton expectation of $C_F/C_A$. Within JEWEL quark and gluon jets lose energy similarly.
