We leverage representation learning and the inductive bias in neural-net-based Standard Model jet classification tasks, to detect non-QCD signal jets. In establishing the framework for classification-based anomaly detection in jet physics, we demonstrate that, with a \emph{well-calibrated} and \emph{powerful enough feature extractor}, a well-trained \emph{mass-decorrelated} supervised Standard Model neural jet classifier can serve as a strong generic anti-QCD jet tagger for effectively reducing the QCD background. Imposing \emph{data-augmented} mass-invariance (and thus decoupling the dominant factor) not only facilitates background estimation, but also induces more substructure-aware representation learning. We are able to reach excellent tagging efficiencies for all the test signals considered. In the best case, we reach a background rejection rate of 51 and a significance improvement factor of 3.6 at 50 \% signal acceptance, with the jet mass decorrelated. This study indicates that supervised Standard Model jet classifiers have great potential in general new physics searches.
Deep learning is a standard tool in the field of high-energy physics, facilitating considerable sensitivity enhancements for numerous analysis strategies. In particular, in identification of physics objects, such as jet flavor tagging, complex neural network architectures play a major role. However, these methods are reliant on accurate simulations. Mismodeling can lead to non-negligible differences in performance in data that need to be measured and calibrated against. We investigate the classifier response to input data with injected mismodelings and probe the vulnerability of flavor tagging…
We demonstrate that the detection of the SM and MSSM Higgs bosons will be possible at the LHC via $t\anti t b\anti b$ and $b\anti b b\anti b$ final state, provided $b$-tagging can be performed with good efficiency and purity.
We demonstrate that expected efficiencies and purities for $b$-tagging at SSC/LHC detectors may allow detection of the Standard Model Higgs in $t\anti t \hsm$ production, with $\hsm\rta b\anti b$ decay, for $80\lsim\mhsm\lsim 130\gev$, provided $\mt\gsim 130\gev$.
Lambda Theta；Zhejiang University（浙江大学）；Asan Medical Center（峨山医学中心）；The University of Western Australia（西澳大学）；Karachi Institute of Economics and Technology（卡拉奇经济技术学院）；Love for Data；Nazarbayev University（纳扎尔巴耶夫大学）
Cancer is one of the most challenging diseases because of its complexity, variability, and diversity of causes. It has been one of the major research topics over the past decades, yet it is still poorly understood. To this end, multifaceted therapeutic frameworks are indispensable. \emph{Anticancer peptides} (ACPs) are the most promising treatment option, but their large-scale identification and synthesis require reliable prediction methods, which is still a problem. In this paper, we present an intuitive classification strategy that differs from the traditional \emph{black box} method and is …
We develop taggers for multi-pronged jets that are simple functions of jet substructure (so-called `subjettiness') variables. These taggers can be approximately decorrelated from the jet mass in a quite simple way. Specifically, we use a Logistic Regression Design (LoRD) which, even being one of the simplest machine learning classifiers, shows a performance which surpasses that of simple variables used by the ATLAS and CMS Collaborations and is not far from more complex models based on neural networks. Contrary to the latter, our method allows for an easy implementation of tagging tasks by pro…
We demonstrate that the classification of boosted, hadronically-decaying weak gauge bosons can be significantly improved over traditional cut-based and BDT-based methods using deep learning and the jet charge variable. We construct binary taggers for $W^+$ vs. $W^-$ and $Z$ vs. $W$ discrimination, as well as an overall ternary classifier for $W^+$/$W^-$/$Z$ discrimination. Besides a simple convolutional neural network (CNN), we also explore a composite of two CNNs, with different numbers of layers in the jet $p_{T}$ and jet charge channels. We find that this novel structure boosts the performa…
Jet flavor tagging with Particle Transformer for Higgs factories
International Center for Elementary Particle Physics, The University of Tokyo（东京大学基础粒子物理国际中心）；Department of Physics, Graduate School of Science, The University of Tokyo（东京大学理学研究科物理学系）；MI-6 Ltd.（MI-6有限公司）
National Tsing Hua University（国立清华大学）；Konkuk University（建国大学）；University of Washington（华盛顿大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；University of California, Berkeley（加州大学伯克利分校）
The modeling of jet substructure significantly differs between Parton Shower Monte Carlo (PSMC) programs. Despite this, we observe that machine learning classifiers trained on different PSMCs learn nearly the same function. This means that when these classifiers are applied to the same PSMC for testing, they result in nearly the same performance. This classifier universality indicates that a machine learning model trained on one simulation and tested on another simulation (or data) will likely be optimal. Our observations are based on detailed studies of shallow and deep neural networks applie…
We construct 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 classifier. In particular, we consider two different decay modes of the Higgs boson, namely into a pair of bottom quarks or into light jets, against the respective backgrounds. For each case, we consider both a moderate- and high- boost scenario. The performance of the tagger is com…
Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surface
Center for Theoretical Physics, Sloane Physics Laboratory, Yale University（理论物理中心，斯洛恩物理实验室，耶鲁大学）；III. Physics Institute A, RWTH Aachen University（物理研究所A，亚琛工业大学）
We present a new tagger which aims at identifying partially reconstructed objects, in which only some of the constituents are collected in a single jet. As an example, we focus on top decays in which either part of the hadronically decaying W or the b jet is soft or falls outside of the top jet cone. We construct an observable to identify remnant substructure from the decay and employ aggressive jet grooming to reject QCD backgrounds. The tagger is complementary to existing ones and works well in the intermediate boost regime where jet substructure techniques usually fail. It is anticipated th…
A method of top tagging is introduced. Using the anti-kt algorithm to define jets, events with nj = 2 fat jets of cone size R = 1.5 are decomposed into R = 0.6 sub-jets and retained if nj (R= 0.6) \geq 4 . One pair of sub-jets reconstructs the W-mass and another jet is tagged as a b-jet, as necessary for hadronic or semileptonic events of tt origin. This 'hollow cone' method distinguishes the tt events from the light parton QCD dijet events. Our simulations are made for the LHC at 7 TeV.
Machine-learning assisted jet substructure tagging techniques have the potential to significantly improve searches for new particles and Standard Model measurements in hadronic final states. Techniques with simple analytic forms are particularly useful for establishing robustness and gaining physical insight. We introduce a procedure to automate the construction of a large class of observables that are chosen to completely specify $M$-body phase space. The procedure is validated on the task of distinguishing $H\rightarrow b\bar{b}$ from $g\rightarrow b\bar{b}$, where $M=3$ and previous brute-f…
University at Buffalo, State University of New York（纽约州立大学布法罗分校）；University of Oregon（俄勒冈大学）
A framework is presented to extract and understand decision-making information from a deep neural network (DNN) 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 both with and without XAUG variables. The XAUG variables are concatenated with the intermediate layers after network-specific operations (such as convolution or recurrence), and used in the final layers of the network. The results of comparing net…
We examine the detection of the intermediate-mass Higgs boson (IMH) at LHC through the associate production channel pp-->t+(anti-t)+H+X-->l+photon+ photon+X'. It is shown that by applying kinematic cuts or b-tagging on the final state jets, the main backgrounds of W(-->l+nu)+photon+photon+(n-jet) can be reduced substantially without significant loss of signals. It is possible to detect the Higgs boson at LHC through the pp-->t+(anti-t)+H+X channel using a modest photon detector with mass resolution of about 3% of the photon pair invariant mass.
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 m…
A method of top tagging is introduced. Using the anti-kt algorithm to define jets, events with nj = 2 fat jets of cone size R = 1.5 are decomposed into R = 0.6 sub-jets and retained if nj (R= 0.6) >= 4 . One pair of sub-jets reconstructs the W-mass and another jet is tagged as a b-jet, as necessary for hadronic or semileptonic events of tt origin. This 'hollow cone' method distinguishes the tt events from the light parton QCD dijet events.
Discriminating QCD Compton and Quark-Antiquark Annihilation Processes in $γ$ + Jets Using Interpretable Machine Learning
Indian Institute of Science Education and Research (IISER), Berhampur（印度科学教育研究所（IISER），贝尔汉普尔）；Indian Institute of Science Education and Research (IISER), Tirupati（印度科学教育研究所（IISER），蒂鲁帕蒂）
Deep-learning jet flavor tagging for precision hadronic Higgs measurements at future $e^+e^-$ Higgs factories
Shanghai Jiao Tong University（上海交通大学）；Tsung-Dao Lee Institute, Shanghai Jiao Tong University（上海交大李政道研究所）；Institute of High Energy Physics, Chinese Academy of Sciences（中国科学院高能物理研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Jet classification is an important ingredient in measurements and searches for new physics at particle coliders, and 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 the classification performance, with a focus on separation of bottom vs. charm flavor tagging. We implement a novel, universal set-to-graph model, which takes into account information from all tracks in a jet to determine if pairs of tracks originated from a common vertex. We explore different performan…
The Latent Information Geometry of Jet Classification
Zentrum für Astronomie der Universität Heidelberg, Astronomisches Rechen-Institut（海德堡大学天文中心，天文计算研究所）；Institut für Theoretische Physik, Universität Heidelberg（海德堡大学理论物理研究所）；Interdisciplinary Center for Scientific Computing (IWR), Universität Heidelberg（海德堡大学跨学科科学计算中心）
Hunting the Unseen: Deep Learning Analysis for Semi-Visible Jet Tagging
University of Southampton（南安普顿大学）；Rutherford Appleton Laboratory（卢瑟福·阿普尔顿实验室）；KIAS（韩国高等科学研究院）；Uppsala University（乌普萨拉大学）；KEK（高能加速器研究机构）；The Graduate University of Advanced Studies (Sokendai)（综合研究大学院大学（索肯代））；Kavli IPMU (WPI), University of Tokyo（东京大学木户宇宙物质研究所（世界顶级研究中心））；University of Manchester（曼彻斯特大学）；CERN（欧洲核子研究组织）
We investigate the use of the event topology as a tool in the search for the six-jet decay of top-pair production in proton-antiproton collisions at 1.8 TeV. Modified Fox-Wolfram "shape" variables, H_i, are employed to help distinguish the top-pair signal from the ordinary QCD multi-jet background. The H's can be constructed directly from the calorimeter cells or from jets. Events are required to lie in a region of H-space defined by L_i < H_i < R_i for i=1,...,,6, where the left, L_i, and right, R_i, cuts are determined by a genetic algorithm (GA) procedure to maximize the signal over the squ…
