Recurrent Quantum Feature Maps for Reservoir Computing
This work proposes a quantum reservoir computing approach for temporal data processing, offering a potential speed advantage over classical methods, though it is incremental as it combines existing concepts.
The authors introduce a reservoir computing model using recurrent quantum feature maps for time-series prediction. On the Mackey-Glass task, it achieves lower mean squared error than classical baselines like echo state networks and multilayer perceptrons, while using compact quantum circuits.
Reservoir computing promises a fast method for handling large amounts of temporal data. This hinges on constructing a good reservoir--a dynamical system capable of transforming inputs into a high-dimensional representation while remembering properties of earlier data. In this work, we introduce a reservoir based on recurrent quantum feature maps where a fixed quantum circuit is reused to encode both current inputs and a classical feedback signal derived from previous outputs. We evaluate the model on the Mackey-Glass time-series prediction task using our recently introduced CP feature map, and find that it achieves lower mean squared error than standard classical baselines, including echo state networks and multilayer perceptrons, while maintaining compact circuit depth and qubit requirements. We further analyze memory capacity and show that the model effectively retains temporal information, consistent with its forecasting accuracy. Finally, we study the impact of realistic noise and find that performance is robust to several noise channels but remains sensitive to two-qubit gate errors, identifying a key limitation for near-term implementations.