Saved in:
Bibliographic Details
Main Authors: Cheng, Chi Lung, Singh, Gup, Nachman, Benjamin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.08889
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915222422290432
author Cheng, Chi Lung
Singh, Gup
Nachman, Benjamin
author_facet Cheng, Chi Lung
Singh, Gup
Nachman, Benjamin
contents 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 Prior-Assisted Weak Supervision (PAWS) method incorporates information from a class of signal models to significantly enhance the search sensitivity of weakly supervised approaches. As long as the true signal is in the pre-specified class, PAWS matches the sensitivity of a dedicated, fully supervised method without specifying the exact parameters ahead of time. On the benchmark LHC Olympics anomaly detection dataset, our mix of semi-supervised and weakly supervised learning is able to extend the sensitivity over previous methods by a factor of 10 in cross section. Furthermore, if we add irrelevant (noise) dimensions to the inputs, classical methods degrade by another factor of 10 in cross section while PAWS remains insensitive to noise. This new approach could be applied in a number of scenarios and pushes the frontier of sensitivity between completely model-agnostic approaches and fully model-specific searches.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08889
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Incorporating Physical Priors into Weakly-Supervised Anomaly Detection
Cheng, Chi Lung
Singh, Gup
Nachman, Benjamin
High Energy Physics - Phenomenology
High Energy Physics - Experiment
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 Prior-Assisted Weak Supervision (PAWS) method incorporates information from a class of signal models to significantly enhance the search sensitivity of weakly supervised approaches. As long as the true signal is in the pre-specified class, PAWS matches the sensitivity of a dedicated, fully supervised method without specifying the exact parameters ahead of time. On the benchmark LHC Olympics anomaly detection dataset, our mix of semi-supervised and weakly supervised learning is able to extend the sensitivity over previous methods by a factor of 10 in cross section. Furthermore, if we add irrelevant (noise) dimensions to the inputs, classical methods degrade by another factor of 10 in cross section while PAWS remains insensitive to noise. This new approach could be applied in a number of scenarios and pushes the frontier of sensitivity between completely model-agnostic approaches and fully model-specific searches.
title Incorporating Physical Priors into Weakly-Supervised Anomaly Detection
topic High Energy Physics - Phenomenology
High Energy Physics - Experiment
url https://arxiv.org/abs/2405.08889