Parameter-Efficient Multilinear Readout for Quantum Reservoir Computing
Abstract
Quantum Reservoir Computing (QRC) uses fixed quantum dynamics as a high-dimensional feature map. Still, standard pipelines flatten reservoir measurements and train a linear readout, ignoring the natural tensor structure across time steps, qubits, and observables. We propose a multilinear readout for quantum reservoir computing (ML-QRC), a tensor-structured neural readout compressed through mode-wise projections. Relative to a dense hidden-width-64 neural readout, this reduces the feature-to-hidden parameter count from 64TnF to d(T+n+F)+64d3, giving a 12.1× feature-block compression at T=50, n=6, d=8, and F=n+binomn2. Across Mackey-Glass forecasting and TFIM phase classification, ML-QRC remains statistically competitive with Ridge on Mackey-Glass and obtains the numerically highest full-data TFIM accuracy among tested methods, while using 12.0× fewer parameters than the full dense MLP. Its clearest benefit is improved low-data stability relative to neural MLP readouts on Mackey-Glass; this advantage does not transfer to TFIM, where Ridge performs best at 50\% data. Overall, ML-QRC is best viewed as a tensor-structured neural readout that compresses dense MLP readouts while preserving QRC tensor structure, rather than as a replacement for simple linear/Ridge readouts in the tested regime.
Related
- Photonic reservoir computing with dimensionally compressed readout
- Parameter-efficient neural computing with programmable photonic meshes
- Reservoir computing generalized: Exploiting complex dynamics via time-invariant transformation
- Nonlinear pluggable optics: Digital signal processing-free Intensity Modulated Direct Detection links using analog photonic Next Generation Reservoir Computing
- Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing
BibTeX
@misc{nguyen2026parameterefficient,
title = {{Parameter-Efficient Multilinear Readout for Quantum Reservoir Computing}},
author = {Van Tien Nguyen and Panagiotis Markopoulos},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.13974},
eprint = {2610.13974},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.13974},
}
RIS
TY - UNPB
TI - Parameter-Efficient Multilinear Readout for Quantum Reservoir Computing
AU - Van Tien Nguyen
AU - Panagiotis Markopoulos
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.13974
UR - https://arxiv.org/abs/2610.13974
AB - Quantum Reservoir Computing (QRC) uses fixed quantum dynamics as a high-dimensional feature map. Still, standard pipelines flatten reservoir measurements and train a linear readout, ignoring the natural tensor structure across time steps, qubits, and observables. We propose a multilinear readout for quantum reservoir computing (ML-QRC), a tensor-structured neural readout compressed through mode-wise projections. Relative to a dense hidden-width-64 neural readout, this reduces the feature-to-hidden parameter count from 64TnF to d(T+n+F)+64d^3, giving a 12.1× feature-block compression at T=50, n=6, d=8, and F=n+binomn2. Across Mackey-Glass forecasting and TFIM phase classification, ML-QRC remains statistically competitive with Ridge on Mackey-Glass and obtains the numerically highest full-data TFIM accuracy among tested methods, while using 12.0× fewer parameters than the full dense MLP. Its clearest benefit is improved low-data stability relative to neural MLP readouts on Mackey-Glass; this advantage does not transfer to TFIM, where Ridge performs best at 50\% data. Overall, ML-QRC is best viewed as a tensor-structured neural readout that compresses dense MLP readouts while preserving QRC tensor structure, rather than as a replacement for simple linear/Ridge readouts in the tested regime.
ER -