When Classical Baselines Are Tuned as Carefully as the Quantum Model, Does Quantum Reservoir Computing Still Win

Jul 16, 2026

Upload by Eden

The work examines whether quantum reservoir computing retains an advantage when classical baselines receive the same level of care as the quantum model—matched size, matched tuning budget, and matched feature capacity. Using exact simulations of small noiseless quantum systems (up to eleven qubits) on prediction tasks, the study tests two commonly cited quantum benefits. In both cases, the advantage disappears under fair comparison: added quantum measurements add no new information beyond a same-size classical formula, while feedback can help quantum reservoirs but well-tuned classical networks still predict more accurately with statistically reliable gaps. Results are reproducible from fixed random seeds and packaged as a benchmarking checklist.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

Abstract

Introduction

Scope and motivation

Related fair-comparison issues

Methods

Common harness and fairness controls

arXiv :2607 .09905v1 [ quant-ph] 10 Jul 2026 When Classical Baselines Are Tuned as Carefully as the Quantum Model, Does Quantum Reservoir Computing Still Win? Tushar Pandey Texas A&M University July 14, 2026 Abstract Can a small quantum computer forecast a changing signal better than an ordinary classical method? Many studies say yes, but the classical methods they compare against are often left in a basic, untuned state while the quantum model is carefully optimised. We ask what happens when the classical competitor is given exactly the same care: the same size and the same amount of tuning effort. We study two popular reasons a quantum reservoir is thought to help, using exact simulations of small quantum systems (up to eleven qubits) on prediction tasks. In both cases the quantum advantage disappears once the comparison is fair. In the first, extra quantum measurements add nothing that a simple classical formula of the same size does not already provide. In the second, a feedback loop genuinely helps the quantum model, turning a useless setup into a working predictor, yet a well-tuned classical network still predicts slightly more accurately, and the gap is statistically reliable. Our point is not that quantum reservoirs can never win, but that two of their commonly cited advantages do not hold up against fair classical competitors at this scale. We provide these matched comparisons as a simple, reusable checklist for honest benchmarking. All results are fully reproducible from fixed random seeds. 1 Introduction Reservoir computing [1 , 2] trains only a linear readout on top of a fixed nonlinear dynamical system, which makes it an attractive near-term application of quantum hardware: a fixed quantum reservoir avoids the trainability pathologies of variational circuits [3] while supplying a high-dimensional nonlinear feature map. Since the original proposals [4 , 5], a growing body of work reports that quantum reservoir computing (QRC) outperforms classical reservoirs andrecurrent networks on chaotic, financial, and biomedical time series [6 , 7] . At the same time, dequantization and expressivity results [8 , 9] caution that the function classes realised by such circuits can often be reproduced classically, which makes the choice of classical baseline decisive. A recurring weakness in these reports is the classical baseline. When a quantum model is compared against an echo-state network (ESN) [1] or a polynomial readout, the strength of the conclusion depends entirely on whether the classical model was given an equal chance: the same feature-space capacity, the same hyperparameter-tuning budget, the same causal evaluation protocol, and a metric that does not implicitly favour the quantum side. In practice these conditions are often not met. Baselines are reported with default settings while the quantum model is tuned; “classical reservoir” refers to a different architecture than the quantum one; efficiency is measured as simulation wall-clock time rather than any hardware-relevant quantity; and directional accuracy is reported without the persistence control that makes it meaningful. This paper asks a narrow question: when the classical baseline is matched in capacity and tuning, does the quantum reservoir’s reported advantage survive? We study two representative advantage mechanisms in noiseless statevector simulation at small system size (q ≤ 11) and find that on these tasks it does not. Our contribution is not the negative outcome per se but the two controls that produce it: a capacity-matched classical model and a tuning-matched classical recurrent network, together with a correctness-gated, deterministic simulation harness. We state the scope plainly: this is a simulation study at sizes that classical hardware can represent exactly (q ≤ 11); the claim is “no advantage here, under fair comparison,” not “no advantage is possible.” We focus on these two advantage mechanisms because they admit the clean

FAQs

What central question does the paper address about quantum reservoir computing?

It asks whether quantum reservoir computing still outperforms classical methods when the classical baseline is tuned with the same capacity and effort as the quantum model.

Which evaluation fairness controls does the methodology emphasize?

It uses causal, leakage-free chronological splits; validation-only tuning for all hyperparameters with equal budget; matched readout feature dimensions; and correctness gates verified by deterministic simulation checks.

What happens to the claimed quantum advantage when comparisons are made fair?

The advantage disappears in both tested mechanisms: extra quantum measurements provide no improvement over an equivalent classical formula, and even when quantum feedback enables prediction, a well-tuned classical network remains slightly but reliably more accurate.

Jul 16, 2026

Upload by Eden