Breaking concentration barriers for quantum extreme learning on digital quantum processors

TL;DR

This paper demonstrates a scalable quantum machine learning approach using superconducting qubits, introducing hyperparameter tuning and eigentask analysis to overcome noise and concentration effects, achieving competitive results on real quantum hardware.

Contribution

It presents a practical quantum extreme learning machine with noise-robust hyperparameter tuning and efficient feature selection, advancing large-scale quantum reservoir computing.

Findings

Achieved quantum machine learning on up to 124 qubits with over 5,000 two-qubit gates.

Identified a transferable optimality regime across different system sizes and tasks.

Attained performance comparable to classical methods on benchmarks.

Abstract

Reservoir computing leverages rich, non-linear dynamics to process temporal data. Quantum variants promise enhanced expressivity from high-dimensional Hilbert spaces, yet their practical applicability is hindered by hardware noise and concentration effects that can erase input-output distinguishability at large system sizes. In this work, we present and experimentally demonstrate a Quantum Extreme Learning Machine (QELM) tailored to state-of-the-art superconducting platforms, employing up to 124 qubits and circuits with more than 5,000 two-qubit gates on IBM Quantum computers. We introduce a practical multi-objective hyperparameter tuning strategy that jointly monitors observable variability, capacity, and task performance to identify noise-robust operating points. In addition, we develop a local eigentask analysis that enables computationally efficient feature selection and effective information retrieval. We report evidence of a regime of optimality that is identifiable at small scales and transferable across tasks and larger systems, and we achieve performances competitive with leading classical baselines on representative benchmarks for time-series forecasting and satellite image classification. Together, our results establish a viable and robust framework for large-scale, pre-fault-tolerant quantum machine learning and provide a foundation for extending reservoir-based methods to more expressive architectures and real-world scenarios.