Towards anomaly detection searches for new physics signatures including Higgs bosons with weakly supervised machine learning
Abstract
The Higgs boson, with its universal coupling to mass, provides a broadly applicable portal to sectors beyond the Standard Model and is therefore a natural anchor for anomaly detection (AD) at collider experiments. The Higgs And X Anomaly Detection (HAXAD) strategy offers a principled approach to searching for such anomalies occurring in association with a Higgs boson by combining machine-learning-based feature embedding, background estimation, and weakly supervised classification. This work extends the previous HAXAD approach towards the level of maturity required for application to recorded collider data. A major addition is the introduction and comparison of two new embedding strategies, which in turn shape the background estimation and classification. In addition, a new inference framework is developed, yielding signal-agnostic and signal-specific cross section limits and thereby completing the statistical machinery needed for future AD analyses built on HAXAD. The set of investigated signal models is also significantly expanded, allowing for the evaluation of sensitivity on a much broader phase space. Improvements to the method increase signal sensitivity with respect to the original method, and when benchmarked against an example cut-based search on the same final state, HAXAD matches or exceeds the best individual cut-based limits for a wide variety of considered signal models. These developments strengthen the case for HAXAD as a viable and compelling AD-based search strategy with novel discovery potential at colliders.
Related
- Deep learning-based self-supervised detection and localization of magnetic resonance imaging anomalies in artificial intelligence-supported radiotherapy workflows
- Low-energy antinuclei measurements for background-free indirect dark matter searches and PBH signatures
- Axion-Like Particle Searches at Muon Colliders: Photon-Neutrino Signatures and Heavy-Neutral-Lepton Feasibility
- Model-independent searches and anomaly detection at the CMS experiment
- Neutralino Dark Matter in SU(5) after H.E.S.S. and Direct-Detection Searches
BibTeX
@misc{cheng2026towards,
title = {{Towards anomaly detection searches for new physics signatures including Higgs bosons with weakly supervised machine learning}},
author = {Chi Lung Cheng and Julia Gonski and Julie Khalilieh Romman and Runze Li and Qibin Liu and Benjamin Nachman and Dennis Noll and Liangyu Wu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.19323},
eprint = {2607.19323},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.19323},
}
RIS
TY - UNPB
TI - Towards anomaly detection searches for new physics signatures including Higgs bosons with weakly supervised machine learning
AU - Chi Lung Cheng
AU - Julia Gonski
AU - Julie Khalilieh Romman
AU - Runze Li
AU - Qibin Liu
AU - Benjamin Nachman
AU - Dennis Noll
AU - Liangyu Wu
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2607.19323
UR - https://arxiv.org/abs/2607.19323
AB - The Higgs boson, with its universal coupling to mass, provides a broadly applicable portal to sectors beyond the Standard Model and is therefore a natural anchor for anomaly detection (AD) at collider experiments. The Higgs And X Anomaly Detection (HAXAD) strategy offers a principled approach to searching for such anomalies occurring in association with a Higgs boson by combining machine-learning-based feature embedding, background estimation, and weakly supervised classification. This work extends the previous HAXAD approach towards the level of maturity required for application to recorded collider data. A major addition is the introduction and comparison of two new embedding strategies, which in turn shape the background estimation and classification. In addition, a new inference framework is developed, yielding signal-agnostic and signal-specific cross section limits and thereby completing the statistical machinery needed for future AD analyses built on HAXAD. The set of investigated signal models is also significantly expanded, allowing for the evaluation of sensitivity on a much broader phase space. Improvements to the method increase signal sensitivity with respect to the original method, and when benchmarked against an example cut-based search on the same final state, HAXAD matches or exceeds the best individual cut-based limits for a wide variety of considered signal models. These developments strengthen the case for HAXAD as a viable and compelling AD-based search strategy with novel discovery potential at colliders.
ER -