Solving Key Challenges in Collider Physics with Foundation Models

Abstract

Foundation Models are neural networks that are capable of simultaneously solving many problems. Large Language Foundation Models like ChatGPT have revolutionized many aspects of daily life, but their impact for science is not yet clear. In this paper, we use a new Foundation Model for hadronic jets to solve three key challenges in collider physics. In particular, we show how experiments can (1) save significant computing power when developing reconstruction algorithms, (2) perform a complete uncertainty quantification for high-dimensional measurements, and (3) search for new physics with model agnostic methods using low-level inputs. In each case, there are significant computational or methodological challenges with current methods that limit the science potential of deep learning algorithms. By solving each problem, we take jet Foundation Models beyond proof-of-principle studies and into the toolkit of practitioners.

arXiv comment5 pages, 2 figures

References in corpus (31)

• The anti-k_t jet clustering algorithm
• FastJet user manual
• Herwig++ Physics and Manual
• Parton distributions with LHC data
• Dispelling the N^3 myth for the Kt jet-finder
• Herwig 7.0 / Herwig++ 3.0 Release Note
• Soft Drop
• Classification without labels: Learning from mixed samples in high energy physics
• Extending the Bump Hunt with Machine Learning
• Systematics of quark/gluon tagging
• OmniFold: A Method to Simultaneously Unfold All Observables
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• SoftKiller, a particle-level pileup removal method
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Particle-level pileup subtraction for jets and jet shapes
• Optimisation of large-radius jet reconstruction for the ATLAS detector in 13 TeV proton-proton collisions
• Presenting Unbinned Differential Cross Section Results
• Symmetries, Safety, and Self-Supervision
• Pileup and Underlying Event Mitigation with Iterative Constituent Subtraction
• Self-supervised Anomaly Detection for New Physics
• Search for new phenomena in two-body invariant mass distributions using unsupervised machine learning for anomaly detection at $\sqrt{s}=13$ TeV with the ATLAS detector
• Machine Learning Methods for Track Classification in the AT-TPC
• Anomaly detection search for new resonances decaying into a Higgs boson and a generic new particle $X$ in hadronic final states using $\sqrt{s}=13$ TeV $pp$ collisions with the ATLAS detector
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• Disentangling Quarks and Gluons with CMS Open Data
• A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications
• Investigating the Topology Dependence of Quark and Gluon Jets
• Multidifferential study of identified charged hadron distributions in $Z$-tagged jets in proton-proton collisions at $\sqrt{s}=$13 TeV
• Unbinned Deep Learning Jet Substructure Measurement in High $Q^2$ ep collisions at HERA
• Anomalies, Representations, and Self-Supervision
• Application of Transfer Learning to Neutrino Interaction Classification

Cited by in corpus (9)

• Machine Learning-Assisted Unfolding for Neutrino Cross-section Measurements with the OmniFold Technique
• Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders
• BitHEP -- The Limits of Low-Precision ML in HEP
• Reconstructing hadronically decaying tau leptons with a jet foundation model
• Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC
• OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
• Tools for Unbinned Unfolding
• Large Language Models -- the Future of Fundamental Physics?
• jBOT: Semantic Jet Representation Clustering Emerges from Self-Distillation