aiqbench analysis
This study provides a rigorous benchmark of simulated quantum reservoir computing for time-series forecasting, demonstrating that classical encoders often outperform gate-based statevector simulations in both accuracy and energy efficiency. The findings highlight the importance of amortized cost accounting and suggest that co-designing feature generators with classical readouts is critical for sustainable AI deployment.
Sustained Performance and Energy Accounting for Nonlinear Forecasting Across Classical and Simulated Quantum Models
arXiv:2510.25183v2 Announce Type: replace-cross Abstract: Energy-efficient AI should be evaluated across the full application pipeline, not only by lowest error or shortest training time. We study this through nonlinear time-series forecasting using simulated quantum reservoir computing (QRC) as an emerging-computing case study. Our evaluation spans 33 forecasting configurations and 825 completed runs on NARMA-10, NARMA-20, Mackey--Glass, Lorenz-63, and Santa Fe laser data. The core benchmark includes 775 fully instrumented runs across statistical, linear, reservoir, neural, continuous-variable Gaussian QRC, and gate-based statevector QRC models, with 50 additional variational QNN runs extending the trainable-quantum comparison. We measure NRMSE, RMSE, MAE, wall time, inference latency, peak CPU/GPU memory, parameter count, operational energy, and carbon. Since a fixed QRC encoder can generate reusable features for multiple readouts, we report both cold-start and amortized costs. We also use a Sustainable Forecasting Score (SFS), a diagnostic geometric mean of normalized predictive skill and log-scaled carbon efficiency, while retaining raw measurements and Pareto analyses. The best mean NRMSE is achieved by continuous-variable QRC with a Transformer readout (0.332), followed closely by classical TCN (0.341) and QRC+TCN (0.340). However, ESN and ridge-lag deliver the strongest sustained efficiency, with average amortized carbon of 0.014 and 0.012 gCO2 per run and SFS values of 0.814 and 0.805. Larger QRC feature maps increase cost without improving average accuracy, while gate-based statevector simulation is not competitive. These results support three practices for emerging AI systems: expose stage-level energy, use reuse-aware accounting boundaries, and co-design the feature generator or accelerator with the classical readout.
Abstract:Energy-efficient AI should be evaluated across the full application pipeline, not only by lowest error or shortest training time. We study this through nonlinear time-series forecasting using simulated quantum reservoir computing (QRC) as an emerging-computing case study. Our evaluation spans 33 forecasting configurations and 825 completed runs on NARMA-10, NARMA-20, Mackey--Glass, Lorenz-63, and Santa Fe laser data. The core benchmark includes 775 fully instrumented runs across statistical, linear, reservoir, neural, continuous-variable Gaussian QRC, and gate-based statevector QRC models, with 50 additional variational QNN runs extending the trainable-quantum comparison. We measure NRMSE, RMSE, MAE, wall time, inference latency, peak CPU/GPU memory, parameter count, operational energy, and carbon. Since a fixed QRC encoder can generate reusable features for multiple readouts, we report both cold-start and amortized costs. We also use a Sustainable Forecasting Score (SFS), a diagnostic geometric mean of normalized predictive skill and log-scaled carbon efficiency, while retaining raw measurements and Pareto analyses. The best mean NRMSE is achieved by continuous-variable QRC with a Transformer readout (0.332), followed closely by classical TCN (0.341) and QRC+TCN (0.340). However, ESN and ridge-lag deliver the strongest sustained efficiency, with average amortized carbon of 0.014 and 0.012 gCO2 per run and SFS values of 0.814 and 0.805. Larger QRC feature maps increase cost without improving average accuracy, while gate-based statevector simulation is not competitive. These results support three practices for emerging AI systems: expose stage-level energy, use reuse-aware accounting boundaries, and co-design the feature generator or accelerator with the classical readout.
6 pages, 1 table, 2 figures. Work conducted under QIntern 2025 (QWorld) with support from Fractal AI Research. Accepted at QCML (PReMI) 2025
Quantum Physics (quant-ph); Machine Learning (cs.LG)
arXiv:2510.25183 [quant-ph]
(or arXiv:2510.25183v2 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2510.25183 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 364 words
