Patrick Kidger works across three distinct disciplines of scientific machine learning: open source software, neural differential equations, and ML for protein engineering. He is the author for much of the open-source scientific JAX ecosystem, holds a visiting lectureship at Imperial College London, and leads much of the ML-for-protein-design at Cradle.bio. He was previously an ML researcher at...
Aishik Ghosh is an incoming professor of AI and physics at Georgia Institute of Technology and currently a postdoctoral scholar at UC Irvine and an affiliate at Berkeley Lab. His focus is on designing high-dimensional statistical methods including uncertainty quantification tools for reliable applications across particle and astrophysics. He also applies AI tools for theoretical physics model...
The accurate simulation of particle showers in collider detectors remains a critical bottleneck for high-energy physics research. Current approaches face fundamental limitations in scalability when modeling the complete shower development process.
Deep generative models offer a promising alternative, potentially reducing simulation costs by orders of magnitude. This capability becomes...
Detailed event simulation at the LHC is taking a large fraction of computing budget. CMS developed an end-to-end ML based simulation framework, called FlashSim, that can speed up the time for production of analysis samples of several orders of magnitude with a limited loss of accuracy. We show how this approach achieves a high degree of accuracy, not just on basic kinematics but on the complex...
We introduce a novel approach for end-to-end black-box optimization of high energy physics (HEP) detectors using local deep learning (DL) surrogates. These surrogates approximate a scalar objective function that encapsulates the complex interplay of particle-matter interactions and physics analysis goals. In addition to a standard reconstruction-based metric commonly used in the field, we...
Given the intense computational demands of full simulation approaches based on traditional Monte Carlo methods, recent fast simulation approaches for calorimeter showers based on deep generative models have received significant attention.
However, for these models to be used in production it is essential for them to be integrated within the existing software ecosystems of experiments. This...
In many domains of science, the likelihood ratio function (LR) is a fundamental ingredient for a variety of statistical methods such as inference, importance sampling, and classification. Neural based LR estimation using probabilistic classification has therefore had a significant impact in these domains, providing a scalable method for determining an intractable LR from simulated datasets via...
We present a case for the use of Reinforcement Learning (RL) for the design of physics instruments as an alternative to gradient-based instrument-optimization methods in [arXiv:2412.10237][1]. Its applicability is demonstrated using two empirical studies. One is longitudinal segmentation of calorimeters and the second is both transverse segmentation as well as longitudinal placement of...
We describe a PU-suppression algorithm for the Global trigger using convolutional neural networks. The network operates on cell towers, exploiting both cluster topology and $E_T$ to correct for the contribution of PU. The algorithm is optimised for firmware deployment, demonstrating high throughput and low resource usage. The small size of the input and lightweight implementation enable a high...
In High Energy Physics (HEP), new discoveries can be enabled by the development of new experiments and the construction of new detectors. Nowadays, many experimental projects rely on the deployment of new detection technologies to build large scale detectors. The validation of these new technologies and their large scale production require an extensive effort in terms of Quality Control.
In...
The search for physics beyond the Standard Model remains one of the primary focus in high-energy physics. Traditional searches at the LHC analyses, though comprehensive, have yet to yield signs of new physics. Anomaly detection has emerged as a powerful tool to widen the discovery horizon, offering a model-agnostic path as way to enhance the sensitivity of generic searches not targeting any...
R-parity violating (RPV) SUSY introduces a wide variety of couplings, making it essential to search without limiting target channels and cover signatures as broadly as possible. Among such signatures, multijet final states offer high inclusivity and are especially well-suited for model-independent searches targeting RPV SUSY scenarios.
In this study, we develop a signal discrimination...
Contrastive learning (CL) has emerged as a powerful technique for constructing low-dimensional yet highly expressive representations of complex datasets, most notably images. Augmentation-based CL — a fully self-supervised strategy — has been the dominant paradigm in particle physics applications, encouraging a model to learn useful features from input data by promoting insensitivity to...
Abstract The fields of High-Energy physics (HEP) and machine learning (ML) converge on the challenge of uncertainty-aware parameter estimation in the presence of data distribution distortions, described in their respective languages --- systematic uncertainties and domain shifts. We present a novel approach based on Contrastive Normalizing Flows (CNFs), which achieved top performance on...
Anomaly detection — identifying deviations from Standard Model predictions — is a key challenge at the Large Hadron Collider due to the size and complexity of its datasets. This is typically addressed by transforming high-dimensional detector data into lower-dimensional, physically meaningful features. We tackle feature extraction for anomaly detection by learning powerful low-dimensional...
The phenomena of Jet Quenching, a key signature of the Quark-Gluon Plasma (QGP) formed in Heavy-Ion (HI) collisions, provides a window of insight into the properties of the primordial liquid. In this study, we evaluate the discriminating power of Energy Flow Networks (EFNs), enhanced with substructure observables, in distinguishing between jets stemming from proton-proton (pp) and jets...
The search for resonant mass bumps in invariant-mass histograms is a fundamental approach for uncovering Beyond the Standard Model (BSM) physics at the LHC. Traditional, model-dependent analyses that utilize this technique, such as those conducted using data from the ATLAS detector, often require substantial resources, which prevent many final states from being explored. Modern machine...
Experimental studies of 𝑏-hadron decays face significant challenges due to a wide range of backgrounds arising from the numerous possible decay channels with similar final states. For a particular signal decay, the process for ascertaining the most relevant background processes necessitates a detailed analysis of final state particles, potential misidentifications, and kinematic overlaps...
Deep generative models have become powerful tools for alleviating the computational burden of traditional Monte Carlo generators in producing high-dimensional synthetic data. However, validating these models remains challenging, especially in scientific domains requiring high precision, such as particle physics. Two-sample hypothesis testing offers a principled framework to address this task....
Ensuring reliable data collection in large-scale particle physics experiments demands Data Quality Monitoring (DQM) procedures to detect possible detector malfunctions and preserve data integrity. Traditionally, this resource-intensive task has been handled by human shifters who may struggle with frequent changes in operational conditions. Instead, to simplify and automate the shifters' work,...
The ATLAS detector at the LHC has comprehensive data quality monitoring procedures for ensuring high quality physics analysis data. This contribution introduces a long short-term memory (LSTM) autoencoder-based algorithm designed to identify detector anomalies in ATLAS liquid argon calorimeter data. The data is represented as a multidimensional time series, corresponding to statistical moments...
The PVFinder algorithm employs a hybrid deep neural network (DNN) approach to reconstruct primary vertices (PVs) in proton-proton collisions at the LHC, addressing the complexities of high pile-up environments in LHCb and ATLAS experiments. By integrating fully connected layers with a UNet architecture, PVFinder’s end-to-end tracks-to-hist DNN processes charged track parameters to predict PV...
Claudius Krause studied physics in Cottbus, Munich, and Lausanne. He received his doctorate in 2016 from Ludwig-Maximilians University Munich, working on “Higgs Effective Field Theories - Systematics and Applications”. He was a postdoctoral researcher at IFIC Valencia in Spain, Fermilab and Rutgers University in the USA, and the University of Heidelberg in Germany. About 6 years ago, he...
The growing luminosity frontier at the Large Hadron Collider is complicating the reconstruction of heavy-hadron collision events both at data acquisition and offline levels with rising particle multiplicities challenging stringent latency and storage requirements. This talk presents significant architectural advancements in Graph Neural Networks (GNNs) aimed at enhancing event reconstruction...
Machine learning model compression methods such as pruning and quantization are critical for enabling efficient inference on resource-constrained hardware. Compression methods are developed independently, and while some libraries attempt to unify these methods under a common interface, they lack integration with hardware deployment frameworks like hls4ml. To bridge this gap, we present PQuant,...
The use of autoencoders for anomaly detection has been extended to many fields of science. Their application in high energy physics is particularly relevant, as a trained model can be used to identify experimental failures, data fluctuations, or—most interestingly—signs of new physics phenomena. In this study, we focus on analyzing event topologies with three leptons, aiming to identify...
The Proton Synchrotron Booster (PSB) accelerates protons with a fundamental radiofrequency (RF) system operating at the revolution frequency, with additional voltage at its second harmonic. Both RF systems are operated in counter-phase for bunch lengthening to reduce space charge effects. To maximise the bunch length , the phase of the voltage at the second harmonic must follow the beam...
Experimental verification of the Higgs trilinear self-coupling is one of the next major challenges of particle physics. While prospects from proton-proton collisions have centred around measuring the on-shell single- and di-Higgs production processes, the off-shell Higgs production process has also been suggested as a complementary channel to resolve the degeneracy in Higgs couplings. We...
For machine learning applications on edge devices, inference speed and hardware resource usage are often limiting factors. These challenges can be mitigated by using model compression techniques such as quantization and pruning. However, these approaches introduce additional hyperparameters that require optimization. Hyperparameter optimization has been widely used to design models with the...
Efficient data processing using machine learning relies on heterogeneous computing approaches, but optimizing input and output data movements remains a challenge. In GPU-based workflows, data already resides on GPU memory, but machine learning models require the input and output data to be provided in sa pecific tensor format, often requiring unnecessary copying outside of the GPU device and...
Alpha Magnetic Spectrometer (AMS-02) is a precision high-energy cosmic-ray experiment on the ISS operating since 2011 and has collected more than 240 billion cosmic ray events. Among them, positrons are important in understanding the particle nature of dark matter. Classifying the positron signals is challenging due to the abundant background of cosmic ray protons. Therefore, we use a...
Machine learning is making its path into natural sciences. A key limitation in ML from a science perspective is the black-box nature of deep neural networks. An alternative is to learn succinct mathematical equations, thus interpretable models, directly from data, allowing for a deeper understanding and scientific reasoning, making the path toward new scientific discovery. Symbolic regression...
With the increasing size of the machine learning (ML) model and vast datasets, the foundation model has transformed how we apply ML to solve real-world problems. Multimodal language models like chatGPT and Llama have expanded their capability to specialized tasks with common pre-train. Similarly, in high-energy physics (HEP), common tasks in the analysis face recurring challenges that demand...
In the end-cap region of the SPD detector complex, particle identification will be provided by a Focusing Aerogel RICH detector (FARICH). FARICH will primarily aid with pion / kaon separation in final open charmonia states (momenta below 5 GeV/c). A free-running (triggerless) data acquisition pipeline to be employed in the SPD results in a high data rate necessitating new approaches to event...
DIPZ is a machine learning algorithm aiming to re-purpose the Deep Impact Parameter Sets (DIPS) jet-flavour taggers to instead regress the jet’s origin vertex position along the beam-line axis. Deployed at the ATLAS High Level Trigger (HLT), the DIPZ labels of each jet in an event are then used in an HLT jet algorithm to construct an event-wide likelihood-based discriminant variable (MLPL),...
The CMS experiment has deployed for the Run 2 LHC data-taking period a Convolutional Neural Network architecture to identify hadronically decaying tau leptons against quark and gluon jets, electrons, and muons: the DeepTau algorithm. For the LHC Run 3, this algorithm saw an important upgrade with the introduction of domain adaptation techniques in order to improve its performance and achieve...
The High-Luminosity Large Hadron Collider (HL-LHC) era promises unprecedented discovery potential but presents significant computational and algorithmic challenges, particularly due to the extreme pileup environment. Accurate and efficient reconstruction of secondary vertices (SVs) originating from the decay of heavy-flavour hadrons or other long-lived particles is critical for key physics...
The interTwin project develops an open-source Digital Twin Engine to integrate application-specific Digital Twins (DTs) across scientific domains. Its framework for the development of DTs supports interoperability, performance, portability and accuracy. As part of this initiative, we implemented the CaloINN normalizing-flow model for calorimeter simulations within the interTwin framework....
The High Luminosity LHC upgrade will require corresponding detector upgrades. At CMS, one of the major improvements will be the new high-granularity endcap calorimeters that will have a much higher granularity, with roughly 3 million hexagonal sensors per endcap having different sizes and thicknesses. Moreover, this detector will provide timing information with an average resolution of ~30ps,...
New physics searches in the highly boosted regime are an essential part of LHC's physics program, aiming at revealing the presence of new heavy resonances predicted by many Beyond Standard Model theories on the high-end of LHC's energy reach.
Within the CMS collaboration numerous jet tagging algorithms have been developed for the identification of hadronic jets originating from the decay of...
The CMS Pixel Detector in Run 3 (about 2 thousand silicon modules) has a fundamental role in tracking and vertexing. Given the detector's aging and potential operational incidents, constant monitoring of its components is essential to ensure the highest data quality. Typically, the Offline Data Quality Monitoring for the CMS Tracker relies on the human inspection of hundreds of histograms, to...
Searches for new particles often span a wide mass range, where both signal and SM background shapes vary significantly. We introduce a multivariate method that fully exploits the correlation between signal and background features and the explored mass scale. The classifiers—either a neural network or boosted decision tree—produce continuous outputs across the full mass range, achieving...
During the data-taking campaigns Run 1 and Run 2, the ALICE collaboration recorded a large amount of proton-proton (pp) collisions across a variety of center-of-mass energies ($\sqrt{s\,}$). This extensive dataset is well suited to study the energy dependence of particle production. Deep neural networks (DNNs) provide a powerful regression tool to capture underlying multidimensional...
Detecting subtle new physics signals, such as those predicted by the Standard Model Effective Field Theory (SMEFT) with small Wilson coefficients, is inherently challenging when individual event-level kinematic differences are marginal. Since all collision events are governed by the same underlying physics parameters, we investigate the predictive power of permutation-invariant neural network...
Particle physics experiments rely on the (generalised) likelihood ratio test (LRT) for searches and measurements. This is not guaranteed to be optimal for composite hypothesis tests, as the Neyman-Pearson lemma pertains only to simple hypothesis tests. An improvement in the core statistical testing methodology would have widespread ramifications across experiments. We discuss an alternate test...
Machine Learning has been an important tool across experiments at the LHC, supporting tasks ranging from simulation and event reconstruction to anomaly detection and physics analysis. These applications demand inference paradigms that are not only efficient and low in latency but also seamlessly integrable into high-energy physics (HEP) workflows. While numerous frameworks exist for the...
The SHiP experiment is a proposed fixed-target experiment at the CERN SPS aimed at searching for feebly interacting particles beyond the Standard Model. One of its main challenges is reducing the large number of muons produced in the beam dump, which would otherwise create significant background in the detector. The muon shield, a system of magnets designed to deflect muons away from the...
Rare event classification in high-energy physics (HEP) plays a crucial role in probing physics beyond the Standard Model (BSM). Such processes serve as indirect searches for new physics by testing deviations from SM predictions in extreme kinematic regimes. The production of four top quarks in association with a ($W^-$) boson at $(\sqrt{s} = 13)$ $ TeV$ is an exceptionally rare SM process with...
I will present recent advancements in developing inclusive, large-scale pretrained models for large-radius jets at the LHC's general-purpose experiments. The discussion will begin with the Sophon model, trained on Delphes datasets as a demonstrative benchmark, and extend to the Global Particle Transformer (GloParT) models, which have been developed and deployed within CMS over the past...
As the High-Luminosity LHC (HL-LHC) era approaches, significant improvements in reconstruction software are required to keep pace with the increased data rates and detector complexity. A persistent challenge for high-throughput GPU-based event reconstruction is the estimation of track parameters, which is traditionally performed using iterative Kalman Filter-based algorithms. While GPU-based...
