Hardware-Aware Tensor Networks for Real-Time Quantum-Inspired Anomaly Detection at Particle Colliders

arXiv cs.LG / 3/30/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper presents quantum-inspired anomaly detection for particle collider events using tensor networks, aiming for real-time deployment at the detector “edge.”
It introduces a spaced matrix product operator (SMPO) designed to be sensitive to multiple beyond-the-Standard-Model benchmark scenarios.
The authors show how the SMPO can be implemented on FPGA hardware with latency and resource usage compatible with trigger systems.
They propose a cascaded SMPO architecture to improve flexibility and efficiency for operation in resource-constrained edge environments.
Overall, the work argues that quantum-inspired ML could be feasible in high-energy collider pipelines ahead of true quantum processor availability.

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.