Challenges for unsupervised anomaly detection in particle physics

  title={Challenges for unsupervised anomaly detection in particle physics},
  author={Katherine Fraser and Samuel Homiller and Rashmish K. Mishra and Bryan Ostdiek and Matthew D. Schwartz},
  journal={Journal of High Energy Physics},
Anomaly detection relies on designing a score to determine whether a particular event is uncharacteristic of a given background distribution. One way to define a score is to use autoencoders, which rely on the ability to reconstruct certain types of data (background) but not others (signals). In this paper, we study some challenges associated with variational autoencoders, such as the dependence on hyperparameters and the metric used, in the context of anomalous signal (top and W) jets in a QCD… 

Creating simple, interpretable anomaly detectors for new physics in jet substructure

This work proposes two strategies that use a small number of high-level observables to mimic the decisions made by the autoencoder on background events, one designed to directly learn the output of the authencoder, and the other designed to learn the difference between the aut Koencoder’s outputs on a pair of events.

‘Flux+Mutability’: a conditional generative approach to one-class classification and anomaly detection

This paper details the implementation of a novel Machine Learning architecture, called Flux+Mutability, which combines cutting-edge conditional generative models with clustering algorithms and describes the possibility of dynamically generating a reference population and defining selection criteria via quantile cuts.

A semi-supervised approach to dark matter searches in direct detection data with machine learning

This work applies modern machine learning techniques to dark matter direct detection by encoding and decoding the graphical representation of background events in the XENONnT experiment with a convolutional variational autoencoder, and demonstrates the reach of learning-focused anomaly detection in this context by comparing results with classical inference.

Anomaly detection in high-energy physics using a quantum autoencoder

It is shown that a simple quantum autoencoder outperforms classical autoencoders for the same inputs and trains very well, and this performance is reproducible on present quantum devices, shows that quantum aut Koencoders are good candidates for analysing high-energy physics data in future LHC runs.

Quantum Anomaly Detection for Collider Physics

An anomaly detection task in the four-lepton state at the Large Hadron Collider that is limited by a small dataset is studied and there is no evidence that QML provides any advantage over classical ML.

Machine-Learning Compression for Particle Physics Discoveries

A new approach for multi-objective learning functions is introduced by simultaneously learning a VAE appropriate for all values of β through parameterization, and it is shown that simulated data compressed by the β -VAE has enough fidelity to distinguish distinct signal morphologies.

Event-Based Anomaly Detection for Searches for New Physics

This paper discusses model-agnostic searches for new physics at the Large Hadron Collider using anomaly-detection techniques for the identification of event signatures that deviate from the Standard

Neural Embedding: Learning the Embedding of the Manifold of Physics Data

: In this paper, we present a method of embedding physics data manifolds with metric structure into lower dimensional spaces with simpler metrics, such as Euclidean and Hyperbolic spaces. We then

Event-based anomaly detection for new physics searches at the LHC using machine learning

This paper discusses model-agnostic searches for new physics at the Large Hadron Collider (LHC) using anomaly-detection techniques for the identification of event signatures that deviate from the

Variational quantum one-class classifier

The algorithm constitutes an extremely compact and effective machine learning model for OCC, which is suitable for noisy intermediate-scale quantum computing because the VQOCC trains a fully-parameterized quantum autoencoder with a normal dataset and does not require decoding.



Autoencoders for unsupervised anomaly detection in high energy physics

Improve the capability of the autoencoder to learn non-trivial features of the jet images, such that it is able to achieve both top jet tagging and the inverse task of QCD jet tagging with the same setup.

Variational autoencoders for anomalous jet tagging

OE, in the context of jet tagging, is employed to facilitate two goals: increasing sensitivity of outlier detection and decorrelating jet mass, and is observed to facilitate excellent results from both aspects.

Topological obstructions to autoencoding

Using a series of illustrative low-dimensional examples, it is shown explicitly how the intrinsic and extrinsic topology of the dataset affects the behavior of an autoencoder and how this topology is manifested in the latent space representation during training.

Anomaly Detection with Conditional Variational Autoencoders

This work exploits the deep conditional variational autoencoder (CVAE) and defines an original loss function together with a metric that targets hierarchically structured data AD and shows the superior performance of this method for classical machine learning (ML) benchmarks and for the application.

Combining outlier analysis algorithms to identify new physics at the LHC

Using super- symmetric benchmark points, it is found that the logical AND combination of the anomaly scores yielded from algorithms trained in the latent space of the VAE is the most effective discriminator of all methods tested.

Novelty Detection Meets Collider Physics

The potential role of novelty detection in collider physics is demonstrated, using autoencoder-based deep neural network and a set of density-based novelty evaluators, which are sensitive to the clustering of unknown-pattern testing data or new-physics signal events for the design of detection algorithms.

Comparing weak- and unsupervised methods for resonant anomaly detection

Anomaly detection techniques are growing in importance at the Large Hadron Collider (LHC), motivated by the increasing need to search for new physics in a model-agnostic way. In this work, we provide

Rare and Different: Anomaly Scores from a combination of likelihood and out-of-distribution models to detect new physics at the LHC

A new method to define anomaly scores and apply this to particle physics collider events is proposed, which is simple to implement and is applicable to other datasets in other fields as well.

Unsupervised outlier detection in heavy-ion collisions

It is shown that the number of reduced (encoded) dimensions to describe a single event contributes significantly to the performance of the outlier detection task and the model which is best suited to separate outlier events is found.

Deep Set Auto Encoders for Anomaly Detection in Particle Physics

A Deep Set Variational Autoencoder is introduced and it is found that the method attains the best anomaly detection ability when there is no decoding step for the network, and the anomaly score is based solely on the representation within the encoded latent space.