arXiv subjects

Maurizio Pierini

Publications and source records attributed to Maurizio Pierini.

At least 91 records · Page 5Linked to original sources

arXiv2020

Fast inference of Boosted Decision Trees in FPGAs for particle physics

We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process. Thanks to its fully on-chip implementation, hls4ml performs inference of Boosted Decision Tree models with extremely low latency. With a typical latency less than 100 ns, this solution is suitable for FPGA-based real-time processing, such as in the Level-1 Trigger system of a collider experiment. These developments open up prospects for physicists to deploy BDTs in FPGAs for identifying the origin of jets, better reconstructing the energies of muons, and enabling better selection of rare signal processes.

physics.comp-ph↗

arXiv2020

JEDI-net: a jet identification algorithm based on interaction networks

We investigate the performance of a jet identification algorithm based on interaction networks (JEDI-net) to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The jet dynamics are described as a set of one-to-one interactions between the jet constituents. Based on a representation learned from these interactions, the jet is associated to one of the considered categories. Unlike other architectures, the JEDI-net models achieve their performance without special handling of the sparse input jet representation, extensive pre-processing, particle ordering, or specific assumptions regarding the underlying detector geometry. The presented models give better results with less model parameters, offering interesting prospects for LHC applications.

hep-ex↗

arXiv2020

Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of particles produced in high-energy physics collisions. We train neural networks on shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

physics.ins-det↗

arXiv2019

Particle Generative Adversarial Networks for full-event simulation at the LHC and their application to pileup description

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 detector geometries. As an example of application, we show how such an architecture could be used as a generator of LHC parasitic collisions (pileup). We present two approaches to generate the events: unconditional generator and generator conditioned on missing transverse energy. We assess generation performances in a realistic LHC data-analysis environment, with a pileup mitigation algorithm applied.

hep-ex↗

arXiv2019

The DNNLikelihood: enhancing likelihood distribution with Deep Learning

We introduce the DNNLikelihood, a novel framework to easily encode, through Deep Neural Networks (DNN), the full experimental information contained in complicated likelihood functions (LFs). We show how to efficiently parametrise the LF, treated as a multivariate function of parameters and nuisance parameters with high dimensionality, as an interpolating function in the form of a DNN predictor. We do not use any Gaussian approximation or dimensionality reduction, such as marginalisation or profiling over nuisance parameters, so that the full experimental information is retained. The procedure applies to both binned and unbinned LFs, and allows for an efficient distribution to multiple software platforms, e.g. through the framework-independent ONNX model format. The distributed DNNLikelihood can be used for different use cases, such as re-sampling through Markov Chain Monte Carlo techniques, possibly with custom priors, combination with other LFs, when the correlations among parameters are known, and re-interpretation within different statistical approaches, i.e. Bayesian vs frequentist. We discuss the accuracy of our proposal and its relations with other approximation techniques and likelihood distribution frameworks. As an example, we apply our procedure to a pseudo-experiment corresponding to a realistic LHC search for new physics already considered in the literature.

hep-ph↗

arXiv2019

FPGA-accelerated machine learning inference as a service for particle physics computing

New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

physics.data-an↗

arXiv2019

Topology classification with deep learning to improve real-time event selection at the LHC

We show how event topology classification based on deep learning could be used to improve the purity of data samples selected in real time at at the Large Hadron Collider. We consider different data representations, on which different kinds of multi-class classifiers are trained. Both raw data and high-level features are utilized. In the considered examples, a filter based on the classifier's score can be trained to retain ~99% of the interesting events and reduce the false-positive rate by as much as one order of magnitude for certain background processes. By operating such a filter as part of the online event selection infrastructure of the LHC experiments, one could benefit from a more flexible and inclusive selection strategy while reducing the amount of downstream resources wasted in processing false positives. The saved resources could be translated into a reduction of the detector operation cost or into an effective increase of storage and processing capabilities, which could be reinvested to extend the physics reach of the LHC experiments.

hep-ex↗

arXiv2019

Learning representations of irregular particle-detector geometry with distance-weighted graph networks

We explore the use of graph networks to deal with irregular-geometry detectors in the context of particle reconstruction. Thanks to their representation-learning capabilities, graph networks can exploit the full detector granularity, while natively managing the event sparsity and arbitrarily complex detector geometries. We introduce two distance-weighted graph network architectures, dubbed GarNet and GravNet layers, and apply them to a typical particle reconstruction task. The performance of the new architectures is evaluated on a data set of simulated particle interactions on a toy model of a highly granular calorimeter, loosely inspired by the endcap calorimeter to be installed in the CMS detector for the High-Luminosity LHC phase. We study the clustering of energy depositions, which is the basis for calorimetric particle reconstruction, and provide a quantitative comparison to alternative approaches. The proposed algorithms provide an interesting alternative to existing methods, offering equally performing or less resource-demanding solutions with less underlying assumptions on the detector geometry and, consequently, the possibility to generalize to other detectors.

physics.data-an↗

arXiv2019

Pileup mitigation at the Large Hadron Collider with Graph Neural Networks

At the Large Hadron Collider, the high transverse-momentum events studied by experimental collaborations occur in coincidence with parasitic low transverse-momentum collisions, usually referred to as pileup. Pileup mitigation is a key ingredient of the online and offline event reconstruction as pileup affects the reconstruction accuracy of many physics observables. We present a classifier based on Graph Neural Networks, trained to retain particles coming from high-transverse-momentum collisions, while rejecting those coming from pileup collisions. This model is designed as a refinement of the PUPPI algorithm, employed in many LHC data analyses since 2015. Thanks to an extended basis of input information and the learning capabilities of the considered network architecture, we show an improvement in pileup-rejection performances with respect to state-of-the-art solutions.

hep-ph↗

arXiv2019

Variational Autoencoders for New Physics Mining at the Large Hadron Collider

Using variational autoencoders trained on known physics processes, we develop a one-sided threshold test to isolate previously unseen processes as outlier events. Since the autoencoder training does not depend on any specific new physics signature, the proposed procedure doesn't make specific assumptions on the nature of new physics. An event selection based on this algorithm would be complementary to classic LHC searches, typically based on model-dependent hypothesis testing. Such an algorithm would deliver a list of anomalous events, that the experimental collaborations could further scrutinize and even release as a catalog, similarly to what is typically done in other scientific domains. Event topologies repeating in this dataset could inspire new-physics model building and new experimental searches. Running in the trigger system of the LHC experiments, such an application could identify anomalous events that would be otherwise lost, extending the scientific reach of the LHC.

hep-ex↗

arXiv2019

LHC analysis-specific datasets with Generative Adversarial Networks

Using generative adversarial networks (GANs), we investigate the possibility of creating large amounts of analysis-specific simulated LHC events at limited computing cost. This kind of generative model is analysis specific in the sense that it directly generates the high-level features used in the last stage of a given physics analyses, learning the N-dimensional distribution of relevant features in the context of a specific analysis selection. We apply this idea to the generation of muon four-momenta in $Z \to μμ$ events at the LHC. We highlight how use-case specific issues emerge when the distributions of the considered quantities exhibit particular features. We show how substantial performance improvements and convergence speed-up can be obtained by including regression terms in the loss function of the generator. We develop an objective criterion to assess the geenrator performance in a quantitative way. With further development, a generalization of this approach could substantially reduce the needed amount of centrally produced fully simulated events in large particle physics experiments.

hep-ex↗

arXiv2018

Detector monitoring with artificial neural networks at the CMS experiment at the CERN Large Hadron Collider

Reliable data quality monitoring is a key asset in delivering collision data suitable for physics analysis in any modern large-scale High Energy Physics experiment. This paper focuses on the use of artificial neural networks for supervised and semi-supervised problems related to the identification of anomalies in the data collected by the CMS muon detectors. We use deep neural networks to analyze LHC collision data, represented as images organized geographically. We train a classifier capable of detecting the known anomalous behaviors with unprecedented efficiency and explore the usage of convolutional autoencoders to extend anomaly detection capabilities to unforeseen failure modes. A generalization of this strategy could pave the way to the automation of the data quality assessment process for present and future high-energy physics experiments.

physics.data-an↗

arXiv2018

Fast inference of deep neural networks in FPGAs for particle physics

Recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA hardware has only just begun. FPGA-based trigger and data acquisition (DAQ) systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. We develop a package based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns.

physics.ins-det↗

arXiv2017

Unitarity Triangle Analysis in the Standard Model and Beyond

Flavour physics represents a unique test bench for the Standard Model (SM). New analyses performed at the LHC experiments are now providing unprecedented insights into CKM metrology and new evidences for rare decays. The CKM picture can provide very precise SM predictions through global analyses. We present here the results of the latest global SM analysis performed by the UTfit collaboration including all the most updated inputs from experiments, lattice QCD and phenomenological calculations. In addition, the Unitarity Triangle (UT) analysis can be used to constrain the parameter space in possible new physics (NP) scenarios. We update here also the UT analysis beyond the SM by the UTfit collaboration. All of the available experimental and theoretical information on $ΔF=2$ processes is reinterpreted including a model-independent NP parametrisation. We determine the allowed NP contributions in the kaon, $D$, $B_d$, and $B_s$ sectors and, in various NP scenarios, we translate them into bounds for the NP scale as a function of NP couplings.

hep-ph↗

arXiv2017

The Global Electroweak and Higgs Fits in the LHC era

We update the global fit to electroweak precision observables, including the effect of the latest measurements at hadron colliders of the $W$ and top-quark masses and the effective leptonic weak mixing angle. We comment on the impact of these measurements in terms of constraints on new physics. We also update the bounds derived from the fit to the Higgs-boson signal strengths, including the observables measured at the LHC Run 2, and compare the improvements with respect to the 7 and 8 TeV results.

hep-ph↗

arXiv2017

Electroweak precision constraints at present and future colliders

We revisit the global fit to electroweak precision observables in the Standard Model and present model-independent bounds on several general new physics scenarios. We present a projection of the fit based on the expected experimental improvements at future $e^+ e^-$ colliders, and compare the constraining power of some of the different experiments that have been proposed. All results have been obtained with the HEPfit code.

hep-ph↗

arXiv2017

Study the effect of beam energy spread and detector resolution on the search for Higgs boson decays to invisible particles at a future e$^+$e$^-$ circular collider

We study the expected sensitivity to measure the branching ratio of Higgs boson decays to invisible particles at a future circular \epem collider (FCC-ee) in the process $e^+e^-\to HZ$ with $Z\to \ell^+\ell^-$ ($\ell=e$ or $μ$) using an integrated luminosity of 3.5 ab$^{-1}$ at a center-of-mass energy $\sqrt{s}=240$ GeV. The impact of the energy spread of the FCC-ee beam and of the resolution in the reconstruction of the leptons is discussed. %Two different detector concepts are considered: a detector corresponding to the CMS reconstruction performances and the expected design of the ILC detector. The minimum branching ratio for a $5σ$ observation after 3.5ab$^{-1}$ of data taking is $1.7\pm 0.1\%(stat+syst) $. The branching ratio exclusion limit at 95\% CL is $0.63 \pm 0.22\%((stat+syst))$.

hep-ex↗

arXiv2016

Combination of Run-1 Exotic Searches in Diboson Final States at the LHC

We perform a statistical combination of the ATLAS and CMS results for the search of a heavy resonance decaying to a pair of vector bosons with the $\sqrt{s}=8$ TeV datasets collected at the LHC. We take into account six searches in hadronic and semileptonic final states carried out by the two collaborations. We consider only public information provided by ATLAS and CMS in the HEPDATA database and in papers published in refereed journals. We interpret the combined results within the context of a few benchmark new physics models, such as models predicting the existence of a {\ensuremath{\mathrm{W^\prime}}\xspace} or a bulk Randall-Sundrum spin--2 resonance, for which we present exclusion limits, significances, $p$-values and best-fit cross sections. A heavy diboson resonance with a production cross section of $\sim$4-5 fb and mass between 1.9 and 2.0 TeV is the exotic scenario most consistent with the experimental results. Models in which a heavy resonance decays preferentially to a WW final state are disfavoured.

hep-ph↗