TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhysCore.7.3.056
TI  - Anomalies, representations, and self-supervision
PY  - 2024/08/16
UR  - https://www.scipost.org/SciPostPhysCore.7.3.056
JF  - SciPost Physics Core
JA  - SciPost Phys. Core
VL  - 7
IS  - 3
SP  - 056
A1  - Dillon, Barry M.
AU  - Favaro, Luigi
AU  - Feiden, Friedrich
AU  - Modak, Tanmoy
AU  - Plehn, Tilman
AB  - We develop a self-supervised method for density-based anomaly detection using contrastive learning, and test it using event-level anomaly data from CMS ADC2021. The AnomalyCLR technique is data-driven and uses augmentations of the background data to mimic non-Standard-Model events in a model-agnostic way. It uses a permutation-invariant Transformer Encoder architecture to map the objects measured in a collider event to the representation space, where the data augmentations define a representation space which is sensitive to potential anomalous features. An AutoEncoder trained on background representations then computes anomaly scores for a variety of signals in the representation space. With AnomalyCLR we find significant improvements on performance metrics for all signals when compared to the raw data baseline.
ER  -

@Article{10.21468/SciPostPhysCore.7.3.056,
	title={{Anomalies, representations, and self-supervision}},
	author={Barry M. Dillon and Luigi Favaro and Friedrich Feiden and Tanmoy Modak and Tilman Plehn},
	journal={SciPost Phys. Core},
	volume={7},
	pages={056},
	year={2024},
	publisher={SciPost},
	doi={10.21468/SciPostPhysCore.7.3.056},
	url={https://scipost.org/10.21468/SciPostPhysCore.7.3.056},
}