Related papers: Extrapolating Jet Radiation with Autoregressive Tr…
Jets are observed in young stellar objects, X-ray sources, active galactic nuclei (AGN). The mechanisms of jet formation may be divided in regular, acting continuously for a long time, and explosive ones. Continuous mechanisms are related…
Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets - collimated showers of particles produced in collisions such as those at the CERN Large Hadron Collider. We explore the use of…
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…
We investigate how a Generative Adversarial Network could be used to generate a list of particle four-momenta from LHC proton collisions, allowing one to define a generative model that could abstract from the irregularities of typical…
The classification of events involving jets as signal-like or background-like can depend strongly on the jet algorithm used and its parameters. This is partly due to the fact that standard jet algorithms yield a single partition of the…
For jets, with great power comes great opportunity. The unprecedented center of mass energies available at the LHC open new windows on the QGP: we demonstrate that jet shape and jet cross section measurements become feasible as a new,…
Initial state radiation, multiple interactions, and event pileup can contaminate jets and degrade event reconstruction. Here we introduce a procedure, jet trimming, designed to mitigate these sources of contamination in jets initiated by…
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…
About one thousand extragalactic large-scale jets are known, and a few tens of them are confirmed sources of infrared, optical, or X-ray photons. Multiwavelength emission comming directly from these outflows is always non-thermal in origin.…
Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the known molecules seen in training. We find that a key limitation is…
Extragalactic relativistic jets are engines able to carry out to large distances a huge amount of power, not only in the form of radiation, but especially in the form of kinetic energy of matter and fields. As such, they can be thought as…
Evaluating loop amplitudes is a time-consuming part of LHC event generation. For di-photon production with jets we show that simple, Bayesian networks can learn such amplitudes and model their uncertainties reliably. A boosted training of…
Generative modeling of high-energy collisions at the Large Hadron Collider (LHC) offers a data-driven route to simulations, anomaly detection, among other applications. A central challenge lies in the hybrid nature of particle-cloud data:…
With the expansion of renewables in the electricity mix, power grid variability will increase, hence a need to robustify the system to guarantee its security. Therefore, Transport System Operators (TSOs) must conduct analyses to simulate…
Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest,…
At the Large Hadron Collider (LHC) it will become possible for the first time to investigate experimentally the forward region in hadron-hadron collisions via high-$p_T$ processes. In the LHC forward kinematics QCD logarithmic corrections…
We present a fast simulation application based on a Deep Neural Network, designed to create large analysis-specific datasets. Taking as an example the generation of W+jet events produced in sqrt(s)= 13 TeV proton-proton collisions, we train…
In the Large Hardron Collider (LHC), multiple proton-proton collisions cause pileup in reconstructing energy information for a single primary collision (jet). This project aims to select the most important features and create a model to…
The properties of decays that take place during jet formation cannot be easily deduced from the final distribution of particles in a detector. In this work, we first simulate a system of particles with well defined masses, decay channels,…
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…