Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC

Abstract

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 representations via contrastive neural embeddings. This approach preserves potential anomalies indicative of new physics and enables rare signal extraction using novel machine learning-based statistical methods for signal-independent hypothesis testing. We compare supervised and self-supervised contrastive learning methods, for both MLP- and Transformer-based neural embeddings, trained on the kinematic observables of physics objects in LHC collision events. The learned embeddings serve as input representations for signal-agnostic statistical detection methods in inclusive final states. We achieve significant improvement in discovery power for both rare new physics signals and rare Standard Model processes across diverse final states, demonstrating its applicability for efficiently searching for diverse signals simultaneously. We study the impact of architectural choices, contrastive loss formulations, supervision levels, and embedding dimensionality on anomaly detection performance. We show that the optimal representation for background classification does not always maximize sensitivity to new physics signals, revealing an inherent trade-off between background structure preservation and anomaly enhancement. We demonstrate that combining compression with domain knowledge for label encoding produces the most effective data representation for statistical discovery of anomalies.

References in corpus (28)

• An Introduction to PYTHIA 8.2
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Learning New Physics from a Machine
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• Global Search for New Physics with 2.0/fb at CDF
• Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
• Model-Independent and Quasi-Model-Independent Search for New Physics at CDF
• Machine Learning for Anomaly Detection in Particle Physics
• A Quasi-Model-Independent Search for New Physics at Large Transverse Momentum
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• A General Search for New Phenomena at HERA
• Symmetries, Safety, and Self-Supervision
• A Quasi-Model-Independent Search for New High p_T Physics at DZero
• Self-supervised Anomaly Detection for New Physics
• Learning new physics efficiently with nonparametric methods
• 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
• MUSiC: a model-unspecific search for new physics in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• 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
• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• Model-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Solving Key Challenges in Collider Physics with Foundation Models
• Neural Embedding: Learning the Embedding of the Manifold of Physics Data
• Model independent search for new phenomena in pp(bar) collisions at sqrt(s) =1.96 TeV
• Anomalies, Representations, and Self-Supervision
• Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models
• Goodness of fit by Neyman-Pearson testing
• Semi-visible jets, energy-based models, and self-supervision