Searching for New Physics with Deep Autoencoders

Abstract

We introduce a potentially powerful new method of searching for new physics at the LHC, using autoencoders and unsupervised deep learning. The key idea of the autoencoder is that it learns to map "normal" events back to themselves, but fails to reconstruct "anomalous" events that it has never encountered before. The reconstruction error can then be used as an anomaly threshold. We demonstrate the effectiveness of this idea using QCD jets as background and boosted top jets and RPV gluino jets as signal. We show that a deep autoencoder can significantly improve signal over background when trained on backgrounds only, or even directly on data which contains a small admixture of signal. Finally we examine the correlation of the autoencoders with jet mass and show how the jet mass distribution can be stable against cuts in reconstruction loss. This may be important for estimating QCD backgrounds from data. As a test case we show how one could plausibly discover 400 GeV RPV gluinos using an autoencoder combined with a bump hunt in jet mass. This opens up the exciting possibility of training directly on actual data to discover new physics with no prior expectations or theory prejudice.

24 pages, 10 figures

References in corpus (21)

• An Introduction to PYTHIA 8.2
• Deep Learning and its Application to LHC Physics
• Classification without labels: Learning from mixed samples in high energy physics
• Anomaly Detection for Resonant New Physics with Machine Learning
• Learning New Physics from a Machine
• A generic anti-QCD jet tagger
• QCD or What?
• Novelty Detection Meets Collider Physics
• Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• Pulling Out All the Tops with Computer Vision and Deep Learning
• Guiding New Physics Searches with Unsupervised Learning
• Pileup Mitigation with Machine Learning (PUMML)
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Probing stop pair production at the LHC with graph neural networks
• Deep Learning as a Parton Shower
• Infrared Safety of a Neural-Net Top Tagging Algorithm
• Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC
• Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case
• Topology classification with deep learning to improve real-time event selection at the LHC
• Deep learning for the R-parity violating supersymmetry searches at the LHC

Cited by in corpus (136)

• Anomaly Detection with Density Estimation
• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Simulation Assisted Likelihood-free Anomaly Detection
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Dijet resonance search with weak supervision using $\sqrt{s}=13$ TeV $pp$ collisions in the ATLAS detector
• The Metric Space of Collider Events
• The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
• Anomaly detection in high-energy physics using a quantum autoencoder
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Tag N' Train: A Technique to Train Improved Classifiers on Unlabeled Data
• Autoencoders for unsupervised anomaly detection in high energy physics
• Anomaly detection with Convolutional Graph Neural Networks
• Deep learning of thermodynamics-aware reduced-order models from data
• Finding New Physics without learning about it: Anomaly Detection as a tool for Searches at Colliders
• Better Latent Spaces for Better Autoencoders
• Variational Autoencoders for Anomalous Jet Tagging
• Simulation-Assisted Decorrelation for Resonant Anomaly Detection
• Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• A robust anomaly finder based on autoencoders
• Bump Hunting in Latent Space
• Exploring the Space of Jets with CMS Open Data
• Machine Learning for Anomaly Detection in Particle Physics
• Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC
• ABCDisCo: Automating the ABCD Method with Machine Learning
• Quark-Gluon Tagging: Machine Learning vs Detector
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Casting a graph net to catch dark showers
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Resonant anomaly detection without background sculpting
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra
• The Hidden Geometry of Particle Collisions
• CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals
• Autoencoders for Semivisible Jet Detection
• Comparing Weak- and Unsupervised Methods for Resonant Anomaly Detection
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Mass Unspecific Supervised Tagging (MUST) for boosted jets
• Equivariant Energy Flow Networks for Jet Tagging
• Symmetries, Safety, and Self-Supervision
• Unsupervised Outlier Detection in Heavy-Ion Collisions
• Per-Object Systematics using Deep-Learned Calibration
• Quantum anomaly detection in the latent space of proton collision events at the LHC
• Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows
• Unravelling physics beyond the standard model with classical and quantum anomaly detection
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Unsupervised Hadronic SUEP at the LHC
• Anomalous Jet Identification via Sequence Modeling
• Topological Obstructions to Autoencoding
• Jet Substructure from Dark Sector Showers
• Learning new physics efficiently with nonparametric methods
• Self-supervised Anomaly Detection for New Physics
• Multiphoton signals of a (96 GeV?) stealth boson
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• 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
• Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions
• 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
• Anomaly Detection in Gravitational Waves data using Convolutional AutoEncoders
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Lorentz group equivariant autoencoders
• What's Anomalous in LHC Jets?
• Probing triple Higgs coupling with machine learning at the LHC
• Anomaly Detection under Coordinate Transformations
• IRC-safe Graph Autoencoder for unsupervised anomaly detection
• Anomaly detection from mass unspecific jet tagging
• Model-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Using a nested anomaly detection machine learning algorithm to study the neutral triple gauge couplings at an \texorpdfstring{$e^{+}{e}^{-}$}{e+e-} collider
• High-dimensional and Permutation Invariant Anomaly Detection
• Detecting anomalous quartic gauge couplings using the isolation forest machine learning algorithm
• Unsupervised in-distribution anomaly detection of new physics through conditional density estimation
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Searching for anomalous quartic gauge couplings at muon colliders using principle component analysis
• Boosting mono-jet searches with model-agnostic machine learning
• A semi-supervised approach to dark matter searches in direct detection data with machine learning
• Machine learning of Kondo physics using variational autoencoders and symbolic regression
• Neural Embedding: Learning the Embedding of the Manifold of Physics Data
• GPU coprocessors as a service for deep learning inference in high energy physics
• Anomalies, Representations, and Self-Supervision
• Nonparametric semisupervised classification for signal detection in high energy physics
• Decoding Dark Matter Substructure without Supervision
• Anomaly Awareness
• A Data-Directed Paradigm for BSM searches: the bump-hunting example
• Taming modeling uncertainties with Mass Unspecific Supervised Tagging
• Learning Multivariate New Physics
• Knowledge-integrated AutoEncoder Model
• Learning to Inflate
• Enhancing the hunt for new phenomena in dijet final-states using anomaly detection filters at the High-Luminosity Large Hadron Collider
• Explainable Representation Learning of Small Quantum States
• Equivariant, Safe and Sensitive -- Graph Networks for New Physics
• Mixture-of-theories Training: Can We Find New Physics and Anomalies Better by Mixing Physical Theories?
• Using k-means assistant event selection strategy to study anomalous quartic gauge couplings at muon colliders
• Jet tagging made easy
• Searching for dark jets with displaced vertices using weakly supervised machine learning
• Model selection and signal extraction using Gaussian Process regression
• A Quantum Algorithm for Model-Independent Searches for New Physics
• Deep learning techniques for Imaging Air Cherenkov Telescopes
• Searching for gluon quartic gauge couplings at muon colliders using the auto-encoder
• Anomaly detection with flow-based fast calorimeter simulators
• Semi-visible jets, energy-based models, and self-supervision
• Detect anomalous quartic gauge couplings at muon colliders with quantum kernel k-means
• Non-resonant Anomaly Detection with Background Extrapolation
• Deep Learning Jet Substructure from Two-Particle Correlation
• Machine learning using rapidity-mass matrices for event classification problems in HEP
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Jet substructure observables for jet quenching in Quark Gluon Plasma: a Machine Learning driven analysis
• Unsupervised and lightly supervised learning in particle physics
• Variational Autoencoders for Jet Simulation
• Jet Classification Using High-Level Features from Anatomy of Top Jets
• Deep Neural Networks to Recover Unknown Physical Parameters from Oscillating Time Series
• Finding Wombling Boundaries in LHC Data with Voronoi and Delaunay Tessellations
• Generative Invertible Quantum Neural Networks
• Detecting anomaly in vector boson scattering
• Semi-supervised permutation invariant particle-level anomaly detection
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Search for periodic signals in the dielectron and diphoton invariant mass spectra using 139 fb${}^{-1}$ of $pp$ collisions at $\sqrt{s}=$ 13 TeV with the ATLAS detector
• Exotic diboson $Z^{\prime }$ decays in the U$\mu \nu$SSM
• Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
• Tensor Network for Anomaly Detection in the Latent Space of Proton Collision Events at the LHC
• Preserving New Physics while Simultaneously Unfolding All Observables
• Image-Based Jet Analysis
• Wasserstein normalized autoencoder for anomaly detection
• Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
• Detecting New Physics as Novelty -- Complementarity Matters
• Learning New Physics from an Imperfect Machine
• Theory, phenomenology, and experimental avenues for dark showers: a Snowmass 2021 report
• Data-driven detector signal characterization with constrained bottleneck autoencoders
• Reweighting and Analysing Event Generator Systematics by Neural Networks on High-Level Features
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure
• Weakly supervised anomaly detection with event-level variables
• Event-level variables for semivisible jets using anomalous jet tagging
• Graph theory inspired anomaly detection at the LHC
• Energy Flow in Particle Collisions