Dr. Aritra Bal, PhD Particle Physicist & ML Researcher
Home About Me Research Publications

Current Work

My research sits at the intersection of quantum computing, machine learning, and experimental particle physics — developing new methods to push the boundaries of what we can discover at the LHC and beyond.

The world need not be binary …

Quantum & Quantum-informed ML
for High-Energy Physics

Quantum computing offers a fundamentally different computational paradigm that may unlock new capabilities for analysing the extraordinarily complex datasets produced at collider experiments. My work in this area explores variational quantum circuits, hybrid classical–quantum architectures and quantum-informed machine learning, asking whether the performance of classical machine learning models can be improved by the usage of quantum circuit-based algorithms, and subsequently lead to a practical advantage for event classification and anomaly detection at the LHC. You can experiment with a qubit visualiser tool here.

Variational Quantum Circuits Quantum Informed Neural Networks Jet Substructure
Must you always know what you are looking for?

Unsupervised ML
for New Physics Searches

The Standard Model of particle physics is extraordinarily successful, yet we know it is incomplete. One of the most pressing challenges at the LHC is searching for signatures of new physics without knowing in advance precisely what we are looking for. Unsupervised and weakly-supervised machine learning methods are ideally suited to this task, enabling model-agnostic anomaly detection directly in collision data.

I develop and apply machine learning models that seek to identify events that deviate from Standard Model expectations, without relying on simulation-based signal assumptions that could bias the search.

Anomaly Detection Autoencoders Normalising Flows Model-Agnostic Searches