ML4Jets2025

Session

Anomaly Detection

Aug 19, 2025, 10:50 AM

CHEN100 (California Institute of Technology)

Conveners

Anomaly Detection

• Benedikt Maier (Imperial College (GB))

Anomaly Detection

• Oz Amram (Fermi National Accelerator Lab. (US))

12. Anomaly detections in 3 lepton channel using AutoEncoders

Alfredo Castaneda (Universidad de Sonora (MX))

8/19/25, 10:50 AM

The use of autoencoders for anomaly detection has been extended to many fields of science. Their application in high energy physics is particularly relevant, as a trained model can be used to identify experimental failures, data fluctuations, or—most interestingly—signs of new physics phenomena. In this study, we focus on analyzing event topologies with three leptons, aiming to identify...

17. Event-level Observables based on Optimal Transport for Resonant Anomaly Detection

Aditya Bhargava

8/19/25, 11:10 AM

We introduce a novel class of event-level observables based on Optimal Transport (OT) and demonstrate their efficacy in collider anomaly detection. Under the weakly supervised Classification Without Labels (CWoLa) framework, we evaluate the discriminative power of OT-derived observables on the LHC Olympics dataset, benchmarking their performance against standard high-level features, with both...

21. Anomaly Detection Results from CMS

Oz Amram (Fermi National Accelerator Lab. (US))

8/19/25, 11:30 AM

Anomaly detection has emerged as a new paradigm for physics analyses enabled by machine learning. This talk will overview the latest results from CMS featuring anomaly detection, highlighting the machine learning techniques employed and the achieved physics performance.

27. Weakly supervised anomaly detection with event-level variables

Liam Brennan (Univ. of California Santa Barbara (US))

8/19/25, 11:50 AM

We introduce a new topology for weakly supervised anomaly detection searches, di-object plus~X. In this topology, one looks for a resonance decaying to two standard model particles produced in association with other anomalous event activity (X). This additional activity is used for classification. We demonstrate how anomaly detection techniques which have been developed for di-jet searches...

39. Improving the model agnostic sensitivity of weakly supervised anomaly detection

Marie Hein (RWTH Aachen University)

8/19/25, 12:10 PM

Weakly supervised anomaly detection can detect new physics at lower cross sections and improve limits without placing many constraints on signal models. For optimal sensitivity across different BSM scenarios, it's important to choose suitable classification architectures and feature sets that offer sensitivity to a wide range of signals. In this study, we explore how to set up such analyses...

41. Testing the Robustness of Via Machinae Stellar Stream Detections Using Resonant Anomaly Detection

Rafael Porto

8/19/25, 12:30 PM

We build upon the results of the Via Machinae stream-finding algorithm, which uses the ANODE method for resonant anomaly detection to search for stellar streams in Gaia data, by employing new tests to identify the stream candidates most likely to represent real stellar streams. We measure the consistency with which candidates are discovered across multiple retrainings of the ANODE neural...

65. Isolating Unisolated Upsilons with Anomaly Detection in CMS Open Data

Radha Mastandrea (LBNL)

8/20/25, 10:50 AM

Proton collisions at the Large Hadron Collider. Using a machine learning (ML)-based anomaly detection strategy, we “rediscover” the Υ in 13 TeV CMS Open Data from 2016, despite overwhelming anti-isolated backgrounds. We elevate the signal significance to 6.4σ using these methods, starting from 1.6σ using the dimuon mass spectrum alone. Moreover, we demonstrate improved sensitivity from using...

58. Incorporating Physical Priors into Weakly-Supervised Anomaly Detection

Gurpreet Singh (University of California, Berkeley)

8/20/25, 11:30 AM

We propose a new machine-learning-based anomaly detection strategy for comparing data with a background-only reference (a form of weak supervision). The sensitivity of previous strategies degrades significantly when the signal is too rare or there are many unhelpful features. Our PriorAssisted Weak Supervision (PAWS) method incorporates information from a class of signal models to...

50. Anomaly Detection applied to the Quality Control of new detector components

Louis Vaslin (KEK High Energy Accelerator Research Organization (JP))

8/20/25, 11:50 AM

In High Energy Physics (HEP), new discoveries depend on the development and deployment of new experimental setups using cutting edge detector technologies. Ensuring the quality of these new detectors is required to ensure the success of such experiments. We propose a tool based on Computer Vision algorithms to improve the reliability and efficiency of the Visual Inspection of new detector...

44. Debiasing Ultrafast Anomaly Detection with Posterior Agreement

Denis-Patrick Odagiu, Denis-Patrick Odagiu (ETH Zurich (CH))

8/20/25, 12:10 PM

The Level-1 Trigger system of the CMS experiment at CERN makes the final decision on which LHC collision data are stored to disk for later analysis. One algorithm used with this scope is an anomaly detection model based on an autoencoder architecture. This model is trained self-supervised on measured data, but its performance is typically evaluated on simulated datasets of potential anomalies....

42. Anomaly Detection in High-Energy Particle Collisions at the LHC

Runze Li (Yale University (US))

8/20/25, 12:30 PM

This contribution presents a novel approach to model-independent anomaly detection in LHC collisions, targeting physics beyond the Standard Model. Leveraging machine learning techniques, we identify potential signals without relying on specific signal models. The analysis employs a machine learning driven background estimation in different signal regions, with weakly supervised classifiers...

59. A Novel Anomaly Detection Approach for Primary Vertex Selection at the HL-LHC

Wasikul Islam (University of Wisconsin-Madison (US))

Vertex selection plays a crucial role in the identification of the hard-scatter primary vertex in high-energy collisions at the Large Hadron Collider (LHC). The high pileup environment at the HL-LHC presents significant challenges, particularly in accurately selecting the hard-scatter vertex. This study investigates an anomaly detection approach, specifically an autoencoder model, for primary...