Multivariate Time Series Forecasting with Gate-Based Quantum Reservoir Computing on NISQ Hardware

2025-10-15

AI Summary

Existing quantum reservoir computing (QRC) approaches are limited to univariate signals and poorly suited for NISQ hardware. This work proposes the first hardware-efficient, gate-based QRC framework for multivariate time-series forecasting. We introduce an injection-memory dual-qubit architecture coupled with Trotterized nearest-neighbor transverse-field Ising dynamics, enabling efficient modeling of dynamical systems under shallow-circuit constraints. Crucially, we identify that native hardware noise acts as implicit regularization, substantially improving linear readout performance. Our method integrates gate-level circuit design, Trotter decomposition, singular value analysis, and NISQ-aware optimization. On the Lorenz-63 and ENSO datasets, it achieves mean squared errors of 0.0087 and 0.0036, respectively—matching classical reservoir computing performance—and outperforms noiseless simulator results on the real IBM Heron R2 quantum processor.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Quantum reservoir computing (QRC) offers a hardware-friendly approach to temporal learning, yet most studies target univariate signals and overlook near-term hardware constraints. This work introduces a gate-based QRC for multivariate time series (MTS-QRC) that pairs injection and memory qubits and uses a Trotterized nearest-neighbor transverse-field Ising evolution optimized for current device connectivity and depth. On Lorenz-63 and ENSO, the method achieves a mean square error (MSE) of 0.0087 and 0.0036, respectively, performing on par with classical reservoir computing on Lorenz and above learned RNNs on both, while NVAR and clustered ESN remain stronger on some settings. On IBM Heron R2, MTS-QRC sustains accuracy with realistic depths and, interestingly, outperforms a noiseless simulator on ENSO; singular value analysis indicates that device noise can concentrate variance in feature directions, acting as an implicit regularizer for linear readout in this regime. These findings support the practicality of gate-based QRC for MTS forecasting on NISQ hardware and motivate systematic studies on when and how hardware noise benefits QRC readouts.

Problem

• Develops quantum reservoir computing for multivariate time series forecasting
• Optimizes quantum circuits for current NISQ hardware constraints and connectivity
• Investigates how hardware noise can benefit quantum reservoir computing performance

Innovation

• Gate-based quantum reservoir computing for multivariate time series
• Trotterized Ising evolution optimized for NISQ device constraints
• Hardware noise acts as implicit regularizer to improve accuracy