Contributor info: Dr Charanjit Kaur Khosa

Charanjit K. Khosa, Veronica Sanz

SciPost Phys. 15, 053 (2023) · published 8 August 2023 | Toggle abstract · pdf

We present a new algorithm for anomaly detection called Anomaly Awareness. The algorithm learns about normal events while being made aware of the anomalies through a modification of the cost function. We show how this method works in different Particle Physics situations and in standard Computer Vision tasks. For example, we apply the method to images from a Fat Jet topology generated by Standard Model Top and QCD events, and test it against an array of new physics scenarios, including Higgs production with EFT effects and resonances decaying into two, three or four subjets. We find that the algorithm is effective identifying anomalies not seen before, and becomes robust as we make it aware of a varied-enough set of anomalies.

Charanjit Kaur Khosa, Veronica Sanz, Michael Soughton

SciPost Phys. Core 5, 050 (2022) · published 2 November 2022 | Toggle abstract · pdf

In this paper we propose ways to incorporate Machine Learning training outputs into a study of statistical significance. We describe these methods in supervised classification tasks using a CNN and a DNN output, and unsupervised learning based on a VAE. As use cases, we consider two physical situations where Machine Learning are often used: high-$p_T$ hadronic activity, and boosted Higgs in association with a massive vector boson.

Charanjit K. Khosa

SciPost Phys. Proc. 10, 011 (2022) · published 10 August 2022 | Toggle abstract · pdf

We study the boosted Higgs tagging using the Lund jet plane. The convolutional neural network is used for the Lund images data set to classify hadronically decaying Higgs from the QCD background. We consider $H\to b \bar{b}$ and $H \to gg$ decay for moderate and high Higgs transverse momentum and compare the performance with the cut based approach using the jet color ring observable. The approach using Lund plane images provides good tagging efficiency for all the cases.

Charanjit Kaur Khosa, Veronica Sanz, Michael Soughton

SciPost Phys. 10, 151 (2021) · published 22 June 2021 | Toggle abstract · pdf

We study the prospects of characterising Dark Matter at colliders using Machine Learning (ML) techniques. We focus on the monojet and missing transverse energy (MET) channel and propose a set of benchmark models for the study: a typical WIMP Dark Matter candidate in the form of a SUSY neutralino, a pseudo-Goldstone impostor in the shape of an Axion-Like Particle, and a light Dark Matter impostor whose interactions are mediated by a heavy particle. All these benchmarks are tensioned against each other, and against the main SM background ($Z$+jets). Our analysis uses both the leading-order kinematic features as well as the information of an additional hard jet. We explore different representations of the data, from a simple event data sample with values of kinematic variables fed into a Logistic Regression algorithm or a Fully Connected Neural Network, to a transformation of the data into images related to probability distributions, fed to Deep and Convolutional Neural Networks. We also study the robustness of our method against including detector effects, dropping kinematic variables, or changing the number of events per image. In the case of signals with more combinatorial possibilities (events with more than one hard jet), the most crucial data features are selected by performing a Principal Component Analysis. We compare the performance of all these methods, and find that using the 2D images of the combined information of multiple events significantly improves the discrimination performance.