High-dimensional and Permutation Invariant Anomaly Detection

Abstract

Methods for anomaly detection of new physics processes are often limited to low-dimensional spaces due to the difficulty of learning high-dimensional probability densities. Particularly at the constituent level, incorporating desirable properties such as permutation invariance and variable-length inputs becomes difficult within popular density estimation methods. In this work, we introduce a permutation-invariant density estimator for particle physics data based on diffusion models, specifically designed to handle variable-length inputs. We demonstrate the efficacy of our methodology by utilizing the learned density as a permutation-invariant anomaly detection score, effectively identifying jets with low likelihood under the background-only hypothesis. To validate our density estimation method, we investigate the ratio of learned densities and compare to those obtained by a supervised classification algorithm.

arXiv comment7 pages, 5 figures

References in corpus (50)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The anti-k_t jet clustering algorithm
• An Introduction to PYTHIA 8.2
• FastJet user manual
• Generative Adversarial Networks
• Dispelling the N^3 myth for the Kt jet-finder
• Score-Based Generative Modeling through Stochastic Differential Equations
• Normalizing Flows: An Introduction and Review of Current Methods
• Echoes of a Hidden Valley at Hadron Colliders
• Anomaly Detection with Density Estimation
• Classification without labels: Learning from mixed samples in high energy physics
• Searching for New Physics with Deep Autoencoders
• Anomaly Detection for Resonant New Physics with Machine Learning
• The Machine Learning Landscape of Top Taggers
• Learning New Physics from a Machine
• Extending the Bump Hunt with Machine Learning
• QCD or What?
• Novelty Detection Meets Collider Physics
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Visible Effects of Invisible Hidden Valley Radiation
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Score-based Generative Models for Calorimeter Shower Simulation
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• Discerning Secluded Sector gauge structures
• Anomaly detection with Convolutional Graph Neural Networks
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Deep Sets
• Perturbative benchmark models for a dark shower search program
• A robust anomaly finder based on autoencoders
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• Via Machinae: Searching for Stellar Streams using Unsupervised Machine Learning
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• How to Understand Limitations of Generative Networks
• 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
• Learning the language of QCD jets with transformers
• 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
• Inductive Simulation of Calorimeter Showers with Normalizing Flows
• What's Anomalous in LHC Jets?
• Jet Diffusion versus JetGPT -- Modern Networks for the LHC
• Anomaly Detection under Coordinate Transformations
• ELSA -- Enhanced latent spaces for improved collider simulations
• The motivation and status of two-body resonance decays after the LHC Run 2 and beyond

Cited by in corpus (10)

• Machine Learning for Anomaly Detection in Particle Physics
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
• Anomaly detection with flow-based fast calorimeter simulators
• Non-resonant Anomaly Detection with Background Extrapolation
• Unifying Simulation and Inference with Normalizing Flows
• Semi-supervised permutation invariant particle-level anomaly detection
• Data-Driven High-Dimensional Statistical Inference with Generative Models
• Variational inference for pile-up removal at hadron colliders with diffusion models