Related papers: Meta-learning and data augmentation for mass-gener…
Jet modification in heavy-ion collisions provides microscopic access to the properties of the quark-gluon plasma. However, conventional approaches based on traditional global observables, such as \(R_{AA}\), capture limited information…
Machine learning has become an essential tool in jet physics. Due to their complex, high-dimensional nature, jets can be explored holistically by neural networks in ways that are not possible manually. However, innovations in all areas of…
We introduce a novel approach to jet tagging and classification through the use of techniques inspired by computer vision. Drawing parallels to the problem of facial recognition in images, we define a jet-image using calorimeter towers as…
We train several neural networks and boosted decision trees to discriminate fully-hadronic boosted di-$\tau$ topologies against background QCD jets, using calorimeter and tracking information. Boosted di-$\tau$ topologies consisting of a…
Meta learning uses information from base learners (e.g. classifiers or estimators) as well as information about the learning problem to improve upon the performance of a single base learner. For example, the Bayes error rate of a given…
We propose a novel model-independent method to search for W' bosons at the Large Hadron Collider by looking at dijets where one jet is identified as a boosted-top jet and another jet is tagged as a boosted-bottom jet. Performing a detector…
We show how weakly supervised machine learning can improve the sensitivity of LHC mono-jet searches to new physics models with anomalous jet dynamics. The Classification Without Labels (CWoLa) method is used to extract all the information…
High-dimensional tensor models are notoriously computationally expensive to train. We present a meta-learning algorithm, MMT, that can significantly speed up the process for spatial tensor models. MMT leverages the property that spatial…
Fast data generation based on Machine Learning has become a major research topic in particle physics. This is mainly because the Monte Carlo simulation approach is computationally challenging for future colliders, which will have a…
The ubiquity of top-rich final states in the context of beyond the Standard Model (BSM) searches has led to their status as extensively studied signatures at the LHC. Over the past decade, numerous endeavours have been undertaken in the…
Convolutional neural networks are basic structures using jet images as input for the jet tagging problems. However, what they have learned during the training process is always difficult to understand just through feature maps. Inspired by…
Jet substructure is playing a central role at the Large Hadron Collider (LHC) probing the Standard Model in extreme regions of phase space and providing innovative ways to search for new physics. Analytic calculations of experimentally…
The jet-jet profile, or detailed manner, in which transverse energy and mass are distributed around the jet-jet system resulting from the hadronic decay of a $Z$ boson in the process Higgs$\to ZZ$ at a proton-proton collider energy of…
This paper reports a detailed study of techniques for identifying boosted, hadronically decaying $W$ bosons using 20fb$^{-1}$ of proton-proton collision data collected by the ATLAS detector at the LHC at a centre-of-mass energy $\sqrt{s} =$…
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.…
An important aspect of the study of Quark-Gluon Plasma (QGP) in ultra-relativistic collisions of heavy ions is the ability to identify, in experimental data, a subset of the jets that were strongly modified by the interaction with the QGP.…
We study the binary discrimination problem of identification of boosted $H\to gg$ decays from massive QCD jets in a systematic expansion in the strong coupling. Though this decay mode of the Higgs is unlikely to be discovered at the LHC, we…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…
High $p_T$ Higgs production at hadron colliders provides a direct probe of the internal structure of the $gg \to H$ loop with the $H \to b\bar{b}$ decay offering the most statistics due to the large branching ratio. Despite the overwhelming…
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…