• Corpus ID: 238856899

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},
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… 
5 Citations

Figures and Tables from this paper

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
Signal-agnostic dark matter searches in direct detection data with machine learning
Juan Herrero-Garcia, ∗ Riley Patrick, † and Andre Scaffidi ‡ Departamento de F́ısica Teórica and IFIC, Universidad de Valencia-CSIC, C/ Catedrático José Beltrán, 2, E-46980 Paterna, Spain ARC Centre
Online-compatible Unsupervised Non-resonant Anomaly Detection
This paper presents a parallel version of the Celada–Seiden cellular automaton that simulates the dynamic response of the immune system to earthquake-triggered tornadoes.
Machine Learning in the Search for New Fundamental Physics
Georgia Karagiorgi,1, ∗ Gregor Kasieczka,2, † Scott Kravitz,3, ‡ Benjamin Nachman,3, 4, § and David Shih5, ¶ 1Department of Physics, Columbia University, New York, NY 10027, USA 2Institut für
Anomaly detection in high-energy physics using a quantum autoencoder
The lack of evidence for new interactions and particles at the Large Hadron Collider has motivated the high-energy physics community to explore model-agnostic dataanalysis approaches to search for


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.
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
Abstract The lack of evidence for new physics at the Large Hadron Collider so far has prompted the development of model-independent search techniques. In this study, we compare the anomaly scores of
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
Unsupervised outlier detection in heavy-ion collisions
We present different methods of unsupervised learning which can be used for outlier detection in high energy nuclear collisions. This method is of particular interest for heavy ion collisions where a
Variational autoencoders for new physics mining at the Large Hadron Collider
A one-sided threshold test to isolate previously unseen processes as outlier events is developed, which could inspire new-physics model building and new experimental searches, and be complementary to classic LHC searches.
Searching for new physics with deep autoencoders
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
Deep Set Auto Encoders for Anomaly Detection in Particle Physics
There is an increased interest in model agnostic search strategies for physics beyond the standard model at the Large Hadron Collider. We introduce a Deep Set Variational Autoencoder and present