Hardware-Aware Tensor Networks for Real-Time Quantum-Inspired Anomaly Detection at Particle Colliders
2026-03-27 • Machine Learning
Machine Learning
AI summaryⓘ
The authors explore how ideas from quantum computing can help find unusual particle collision events that might show new physics beyond what we already know. They use a method called tensor networks to detect these anomalies in real time during collider experiments. Specifically, they design a special model called the spaced matrix product operator (SMPO) that works efficiently on existing hardware and can be used immediately in current scientific setups. They also propose an improved version, the cascaded SMPO, which is even better suited for devices with limited computing power. Overall, their work shows it's possible to apply quantum-inspired machine learning now to help discover new physics.
quantum machine learningtensor networksanomaly detectionbeyond the Standard Modelcollider detectorsmatrix product operatorfield programmable gate arraytrigger systemsquantum-inspired algorithmsedge computing
Authors
Sagar Addepalli, Prajita Bhattarai, Abhilasha Dave, Julia Gonski
Abstract
Quantum machine learning offers the ability to capture complex correlations in high-dimensional feature spaces, crucial for the challenge of detecting beyond the Standard Model physics in collider events, along with the potential for unprecedented computational efficiency in future quantum processors. Near-term utilization of these benefits can be achieved by developing quantum-inspired algorithms for deployment in classical hardware to enable applications at the "edge" of current scientific experiments. This work demonstrates the use of tensor networks for real-time anomaly detection in collider detectors. A spaced matrix product operator (SMPO) is developed that provides sensitivity to a variety beyond the Standard Model benchmarks, and can be implemented in field programmable gate array hardware with resources and latency consistent with trigger deployment. The cascaded SMPO architecture is introduced as an SMPO variation that affords greater flexibility and efficiency in ways that are key to edge applications in resource-constrained environments. These results reveal the benefit and near-term feasibility of deploying quantum-inspired ML in high energy colliders.