Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows

Abstract

We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event representations, anomaly score definitions, network architectures) affect the result on specific benchmark new physics models. Once a baseline is established, we discuss how to improve the anomaly detection accuracy by exploiting normalizing flow layers in the latent space of the variational autoencoder.

arXiv comment10 + 3 pages, 7 figures

References in corpus (34)

• Scikit-learn: Machine Learning in Python
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• Normalizing Flows: An Introduction and Review of Current Methods
• Trial factors for the look elsewhere effect in high energy physics
• Performance of the CMS Level-1 trigger in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Anomaly Detection with Density Estimation
• Searching for New Physics with Deep Autoencoders
• Anomaly Detection for Resonant New Physics with Machine Learning
• Learning New Physics from a Machine
• Extending the Bump Hunt with Machine Learning
• Graph Neural Networks in Particle Physics
• Improving Variational Inference with Inverse Autoregressive Flow
• QCD or What?
• Operation of the ATLAS trigger system in Run 2
• Simulation Assisted Likelihood-free Anomaly Detection
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Guiding New Physics Searches with Unsupervised Learning
• Variational Autoencoders for New Physics Mining at the Large Hadron Collider
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Sylvester Normalizing Flows for Variational Inference
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Autoencoders for unsupervised anomaly detection in high energy physics
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• Global Search for New Physics with 2.0/fb at CDF
• A strategy for a general search for new phenomena using data-derived signal regions and its application within the ATLAS experiment
• Learning the latent structure of collider events
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• A General Search for New Phenomena at HERA
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• Model independent search for new phenomena in pp(bar) collisions at sqrt(s) =1.96 TeV
• Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow

Cited by in corpus (17)

• Machine Learning for Anomaly Detection in Particle Physics
• CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• What's Anomalous in LHC Jets?
• Anomaly Detection under Coordinate Transformations
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Anomalies, Representations, and Self-Supervision
• Event-based anomaly detection for new physics searches at the LHC using machine learning
• Calorimeter shower superresolution
• End-to-end simulation of particle physics events with Flow Matching and generator Oversampling
• Model selection and signal extraction using Gaussian Process regression
• Semi-visible jets, energy-based models, and self-supervision
• Non-resonant Anomaly Detection with Background Extrapolation
• TopicFlow: Disentangling quark and gluon jets with normalizing flows
• Event Generation and Density Estimation with Surjective Normalizing Flows
• Graph theory inspired anomaly detection at the LHC
• It's not a FAD: first results in using Flows for unsupervised Anomaly Detection at 40 MHz at the Large Hadron Collider