Photonic reservoir computing with dimensionally compressed readout
Abstract
This work addresses a hardware constraint in reservoir computing: the limited size of the readout layer imposed by systems with a physical readout. We investigate a strategy to accommodate this constraint based on random projection, which compresses high-dimensional reservoir states into a lower-dimensional subspace while preserving key properties of the source space and information- processing capabilities. To evaluate this approach, we compare a small, standalone time delay reservoir against a larger configuration whose output is projected down to match the same restricted readout dimension. Using task-independent metrics, we demonstrate that the distribution of information-processing capacities may differ between the two configurations, even at identical readout sizes. Furthermore, we perform a comprehensive hyperparameter scan to assess how both systems behave under varying physical regimes. Finally, we benchmark this approach on the standard NARMA10 task, showing that the random projection framework can yield superior performance compared to a standalone constrained reservoir, within specific compression range. These results provide a scalable pathway to bypass physical readout bottlenecks in hardware-based reservoir computing.
Related
- Nonlinear pluggable optics: Digital signal processing-free Intensity Modulated Direct Detection links using analog photonic Next Generation Reservoir Computing
- Parameter-Efficient Multilinear Readout for Quantum Reservoir Computing
- Frequency-Multiplexed Photonic Reservoir Computing with a Synchronously Pulse-Driven Optical Cavity
- When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing
- Photonic reservoir computing with complex networks
BibTeX
@misc{kobi2026photonic,
title = {{Photonic reservoir computing with dimensionally compressed readout}},
author = {Gerald Kobi and Mohab Abdalla and Miguel C. Soriano and Damien Rontani},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.07418},
eprint = {2609.07418},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.07418},
}
RIS
TY - UNPB
TI - Photonic reservoir computing with dimensionally compressed readout
AU - Gerald Kobi
AU - Mohab Abdalla
AU - Miguel C. Soriano
AU - Damien Rontani
PY - 2026
DA - 2026/09/07
PB - arXiv
DO - 10.48550/arxiv.2609.07418
UR - https://arxiv.org/abs/2609.07418
AB - This work addresses a hardware constraint in reservoir computing: the limited size of the readout layer imposed by systems with a physical readout. We investigate a strategy to accommodate this constraint based on random projection, which compresses high-dimensional reservoir states into a lower-dimensional subspace while preserving key properties of the source space and information- processing capabilities. To evaluate this approach, we compare a small, standalone time delay reservoir against a larger configuration whose output is projected down to match the same restricted readout dimension. Using task-independent metrics, we demonstrate that the distribution of information-processing capacities may differ between the two configurations, even at identical readout sizes. Furthermore, we perform a comprehensive hyperparameter scan to assess how both systems behave under varying physical regimes. Finally, we benchmark this approach on the standard NARMA10 task, showing that the random projection framework can yield superior performance compared to a standalone constrained reservoir, within specific compression range. These results provide a scalable pathway to bypass physical readout bottlenecks in hardware-based reservoir computing.
ER -