TY  - JOUR
AU  - van Beekveld, M.
AU  - Caron, S.
AU  - Hendriks, L.
AU  - Jackson, P.
AU  - Leinweber, A.
AU  - Otten, S.
AU  - Patrick, R.
AU  - Ruiz de Austri, R.
AU  - Santoni, M.
AU  - White, M.
PY  - 2021
DA  - 2021//
TI  - Combining outlier analysis algorithms to identify new physics at the LHC
T2  - J. High Energy Phys.
JO  - Journal of High Energy Physics
SP  - 024
EP  - 33pp
VL  - 09
IS  - 9
PB  - Springer
KW  - Phenomenological Models
KW  - Supersymmetry Phenomenology
AB  - The lack of evidence for new physics at the Large Hadron Collider so far has prompted the development of model-independent search techniques. In this study, we compare the anomaly scores of a variety of anomaly detection techniques: an isolation forest, a Gaussian mixture model, a static autoencoder, and a beta-variational autoencoder (VAE), where we define the reconstruction loss of the latter as a weighted combination of regression and classification terms. We apply these algorithms to the 4-vectors of simulated LHC data, but also investigate the performance when the non-VAE algorithms are applied to the latent space variables created by the VAE. In addition, we assess the performance when the anomaly scores of these algorithms are combined in various ways. Using supersymmetric benchmark points, we find that the logical AND combination of the anomaly scores yielded from algorithms trained in the latent space of the VAE is the most effective discriminator of all methods tested.
SN  - 1029-8479
UR  - https://arxiv.org/abs/2010.07940
UR  - https://doi.org/10.1007/JHEP09(2021)024
DO  - 10.1007/JHEP09(2021)024
LA  - English
N1  - WOS:000695421600003
ID  - vanBeekveld_etal2021
ER  -