ML4Jets2022

Session

Anomaly Detection

2 Nov 2022, 09:00

Multipurpose Room (aka Livingston Hall) (Rutgers University)

Conveners

Anomaly Detection

• Elham E Khoda (University of Washington (US))
• Dylan Sheldon Rankin (Massachusetts Inst. of Technology (US))

Anomaly Detection

• Barry Dillon (University of Heidelberg)
• Lawrence Lee Jr (University of Tennessee (US))

Anomaly Detection

• Yuri Gershtein (Rutgers State Univ. of New Jersey (US))
• David Shih

86. Introduction to Anomaly Detection

Dr Barry Dillon (University of Heidelberg)

02/11/2022, 09:00

I will give an overview of recent progress in less-than-supervised methods for new physics searches at the LHC.

10. Results from Unsupervised Machine Learning in an ATLAS Dijet Resonance Search

Julia Lynne Gonski (Columbia University (US))

02/11/2022, 09:25

An application of unsupervised machine learning-based anomaly detection to a generic dijet resonance is presented using the full LHC Run 2 dataset collected by ATLAS. A novel variational recurrent neural network (VRNN) is trained over data, specifically large-radius jets that are modeled using a sequence of constituent four-vectors and substructure variables, to identify anomalous jets based...

52. A Normalized Autoencoder for LHC triggers

Luigi Favaro

02/11/2022, 09:45

The main goal for the upcoming LHC runs is still to discover BSM physics. It will require analyses able to probe regions not linked to specific models but generally identified as beyond the Standard Model. Autoencoders are the typical choice for fast anomaly detection models. However, they have shown to misidentify anomalies of low complexity signals over background events. I will present an...

62. Robust anomaly detection using NuRD

Abhijith Gandrakota (Fermi National Accelerator Lab. (US))

02/11/2022, 10:05

Anomaly Detection algorithms are crucial tools for identifying unusual decays from proton collisions at the LHC and are efficient methods for seeking out the possibility of new physics. These detection algorithms should be robust against nuisance kinematic variables and detector conditions. To achieve this robustness, popular detection models built via autoencoders, for example, have to go...

12. Challenges for unsupervised anomaly detection in particle physics

Katherine Fraser (Harvard University)

02/11/2022, 10:25

I discuss several approaches to anomaly detection in collider physics, including using variational autoencoders, which rely on the ability to reconstruct certain types of data (background) but not others (signals), and optimal transport distances, which which measures how easily one pT distribution can be changed into another. I discuss advantages and challenges associated with each approach....

33. CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transporting Adjacent INtervals

Johnny Raine (Universite de Geneve (CH))

03/11/2022, 14:00

We introduce a new model independent technique for constructing background data templates for use in searches for new physics processes at the LHC.

This method, called CURTAINs, uses invertible neural networks to parametrise the distribution of side band data as a function of the resonant observable. The network learns a transformation to map any data point from its value of the resonant...

66. Generative Models for Resonant Anomaly Detection

Elham E Khoda (University of Washington (US))

03/11/2022, 14:20

Machine learning-based anomaly detection techniques offer exciting possibilities to significantly extend the search for new physics at the Large Hadron Collider (LHC) and elsewhere by reducing the model dependence. In this work, we focus on resonant anomaly detection, where generative models can be trained in sideband regions and interpolated into a signal region to provide an estimate of the...

31. HEP-Sim2Real: creating background templates with normalizing flows

Radha Mastandrea (University of California, Berkeley)

03/11/2022, 14:40

Resonant anomaly detection is a promising framework for model-independent searches for new particles. Weakly supervised resonant anomaly detection methods compare data with a potential signal against a template of the Standard Model (SM) background inferred from sideband regions. We propose a means to generate this background template that uses a normalizing flow to create a mapping between...

61. Weakly supervised methods for LHC analyses

Thorben Finke

03/11/2022, 15:00

We investigate how weakly supervised methods like CWoLa and CATHODE can be used to enhance the sensitivity of searches at the LHC. These methods do not rely on truth level labels and are thus applicable in a model agnostic setting. In particular, we examine how these methods generalize to low level features, i.e. to higher dimensional inputs. As one example, we show how CWoLa can enhance the...

84. Resonant anomaly detection without background sculpting

Manuel Sommerhalder (Hamburg University (DE))

03/11/2022, 15:20

We introduce a new technique named Latent CATHODE (LaCATHODE) for performing "enhanced bump hunts", a type of resonant anomaly search that combines conventional one-dimensional bump hunts with a model-agnostic anomaly score in an auxiliary feature space where potential signals could also be localized. The main advantage of LaCATHODE over existing methods is that it provides an anomaly score...

96. Anomaly detection in a perspective of interdisciplinary research

Taoli Cheng (University of Montreal)

04/11/2022, 14:00

Zoom

Following the previous work of leveraging Standard Model jet classifiers as generic anomalous jet taggers (https://arxiv.org/abs/2201.07199), we present an analysis of regularized SM jet classifiers serving as anti-QCD taggers. In the second part of the presentation, from the perspective of interdisciplinary research, we initiate a discussion on the opportunities and challenges involved in the...

18. Optimal Mass Variables for Semivisible Jets

Kevin Pedro (Fermi National Accelerator Lab. (US))

04/11/2022, 14:20

We apply the artificial event variable technique, a deep neural network with an information bottleneck, to strongly coupled hidden sector models. These models of physics beyond the standard model predict collider production of invisible, composite dark matter candidates mixed with regular hadrons in the form of semivisible jets. We explore different resonant production mechanisms to determine...

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

Sang Eon Park (Massachusetts Inst. of Technology (US))

04/11/2022, 14:40

There is a growing recent interest in endowing the space of collider events with a metric structure calculated directly in the space of its inputs. For quarks and gluons, the recently developed energy mover's distance has allowed for a quantification of what is different between physical events. However, the large number of particles within jets makes using metrics and interpreting these...

64. Hunting for signals using Gaussian Process regression

Abhijith Gandrakota (Fermi National Accelerator Lab. (US))

04/11/2022, 15:00

We present a novel computational approach for extracting weak signals, whose exact location and width may be unknown, from complex background distributions with an arbitrary functional form. We focus on datasets that can be naturally presented as binned integer counts, demonstrating our approach on the datasets from the Large Hadron Collider. Our approach is based on Gaussian Process (GP)...