Publications

01 2026

In peer-review

From Information Geometry to Jet Substructure: A Triality of Cumulant Tensors, Energy Correlators, and Hypergraphs

Aritra Bal, Markus Klute, Benedikt Maier, Michael Spannowsky

Pairwise Fisher graphs capture local covariance information, but they cannot distinguish an irreducible multi-observable radiation pattern from a collection of ordinary pairwise correlations. We show that this missing structure is naturally supplied by higher-order Fisher tensors. In a finite basis of binned EECs, ECFs, or EFPs, and in the natural exponential-family coordinates generated by that basis, the same local tensor has three equivalent interpretations: a coefficient in the local Kullback-Leibler expansion, a connected cumulant of the chosen correlator observables, and a signed weight on a hyperedge linking those observables. This gives an exact Fisher-correlator-hypergraph triality in the local exponential-family embedding. The triality provides a direct construction of physics-informed hypergraphs from correlator data. Extending the quadratic Fisher matrix to the first non-trivial higher tensor identifies genuinely connected multi-observable radiation patterns, supplies hyperedge weights for higher-order Laplacians and message passing, and gives a principled criterion for compressing observable bases beyond pairwise information. We develop these constructions and spell out why the exact cumulant interpretation is special to natural exponential-family coordinates. We illustrate the framework in four applications. In a minimal local-KL study, the cubic Fisher tensor reduces the KL truncation error and isolates the dominant triplet structure. In a two-versus-three prong jet substructure benchmark, the hypergraph selector improves compressed-basis classification. In a 33-observable basis-design problem, the Fisher hypergraph retains more third-order local response at twelve observables. A low-capacity learning benchmark then shows how the same Fisher hyperedges can be used as an interpretable inductive bias for message passing on correlator observables.

arXiv PDF

02 2026

In preparation for publication

Machine learning techniques for model-independent searches in dijet final states

CMS Collaboration

We present the performance of machine learning-based anomaly detection techniques for extracting potential new physics phenomena in a model-agnostic way with the CMS experiment at the LHC. We introduce five distinct outlier detection or density estimation techniques — CWoLa, Tag N'Train, CATHODE, QUAK, and QR-VAE — tailored for the identification of anomalous jets originating from the decay of unknown heavy particles. We demonstrate the utility of these approaches in enhancing the sensitivity to a wide variety of potential signals and assess their comparative performance in simulation.

CDS arXiv PDF

03 2025

In peer-review

QINNs: Quantum-Informed Neural Networks

Aritra Bal, Markus Klute, Benedikt Maier, Melik Oughton, Eric Pezone, Michael Spannowsky

Classical deep neural networks can learn rich multi-particle correlations in collider data, but their inductive biases are rarely anchored in physics structure. We propose quantum-informed neural networks (QINNs), a general framework that brings quantum information concepts and quantum observables into purely classical models. While the framework is broad, in this paper we study one concrete realisation that encodes each particle as a qubit and uses the Quantum Fisher Information Matrix (QFIM) as a compact, basis-independent summary of particle correlations. Using jet tagging as a case study, QFIMs act as lightweight embeddings in graph neural networks, increasing model expressivity and plasticity. The QFIM reveals distinct patterns for QCD and hadronic top jets that align with physical expectations. QINNs offer a practical, interpretable, and scalable route to quantum-informed analyses of particle collisions, particularly by enhancing well-established deep learning approaches.

arXiv PDF GitHub

04 2025

Published in Physical Review D EPS HEP 2025 · ML4Jets 2025

One Particle – One Qubit: Particle Physics Data Encoding for Quantum Machine Learning

Aritra Bal, Markus Klute, Benedikt Maier, Melik Oughton, Eric Pezone, Michael Spannowsky

We introduce 1P1Q, a novel quantum data encoding scheme for high-energy physics (HEP), where each particle is assigned to an individual qubit, enabling direct representation of collision events without classical compression. We demonstrate the effectiveness of 1P1Q in quantum machine learning (QML) through two applications: a Quantum Autoencoder (QAE) for unsupervised anomaly detection and a Variational Quantum Circuit (VQC) for supervised classification of top quark jets. The QAE successfully distinguishes signal jets from background QCD jets, achieving superior performance compared to a classical autoencoder while utilising significantly fewer trainable parameters. The VQC achieves competitive classification performance approaching state-of-the-art classical models despite minimal computational complexity. We additionally validate the QAE on real experimental data from the CMS detector, establishing the robustness of quantum algorithms in practical HEP applications.

PRD arXiv PDF

05 2025

Published in Reports on Progress in Physics ML4Jets 2024

Model-agnostic search for dijet resonances with anomalous jet substructure in proton–proton collisions at √s = 13 TeV

CMS Collaboration

This paper presents a model-agnostic search for narrow resonances in the dijet final state in the mass range 1.8–6 TeV. The signal is assumed to produce jets with substructure atypical of jets initiated by light quarks or gluons, with minimal additional assumptions. A collection of complementary anomaly detection methods — based on unsupervised, weakly supervised, and semisupervised algorithms — are used to maximise the sensitivity to unknown new physics signatures. These algorithms are applied to data corresponding to an integrated luminosity of 138 fb⁻¹ recorded by the CMS experiment at √s = 13 TeV. No significant excesses above background expectations are seen. The anomaly detection methods are found to significantly enhance the sensitivity to a variety of models relative to benchmark inclusive and substructure-based search strategies.

RoPP arXiv CDS ML4Jets PDF

06 2024

Published in Machine Learning: Science and Technology

Distilling particle knowledge for fast reconstruction at high-energy physics experiments

Aritra Bal, Tristan Brandes, Fabio Iemmi, Markus Klute, Benedikt Maier, Vinicius Mikuni, Thea Klaeboe Aarrestad

Knowledge distillation is a form of model compression that allows artificial neural networks of different sizes to learn from one another. We consider proton-proton collisions at the High-Luminosity LHC and demonstrate a successful knowledge transfer from an event-level graph neural network (GNN) to a particle-level small deep neural network (DNN). Our algorithm, DistillNet, is trained to predict whether a particle originates from the primary interaction vertex. The results show minimal loss during knowledge transfer to the student network while significantly improving computational resource requirements. This is demonstrated on a CPU and for a quantized and pruned student network deployed on an FPGA, proving the utility of this approach for fast AI in high-energy physics trigger stages.

MLST arXiv INSPIRE PDF