Bridging Theory and Practice in Crafting Robust Spiking Reservoirs

TL;DR

This paper introduces the robustness interval as a practical measure for tuning spiking reservoirs, demonstrating its effectiveness across various configurations and tasks, and validating the critical point as a reliable starting point.

Contribution

It bridges theoretical criticality with practical stability by defining and analyzing the robustness interval in spiking reservoir computing, supported by extensive experiments.

Findings

Robustness interval width decreases with network sparsity and firing threshold.

Specific parameter pairs preserve the analytical critical point, forming iso-performance manifolds.

The critical point consistently lies within high-performance regions, aiding parameter tuning.

Abstract

Spiking reservoir computing provides an energy-efficient approach to temporal processing, but reliably tuning reservoirs to operate at the edge-of-chaos is challenging due to experimental uncertainty. This work bridges abstract notions of criticality and practical stability by introducing and exploiting the robustness interval, an operational measure of the hyperparameter range over which a reservoir maintains performance above task-dependent thresholds. Through systematic evaluations of Leaky Integrate-and-Fire (LIF) architectures on both static (MNIST) and temporal (synthetic Ball Trajectories) tasks, we identify consistent monotonic trends in the robustness interval across a broad spectrum of network configurations: the robustness-interval width decreases with presynaptic connection density $\beta$ (i.e., directly with sparsity) and directly with the firing threshold $\theta$. We further identify specific $(\beta, \theta)$ pairs that preserve the analytical mean-field critical point $w_{\text{crit}}$, revealing iso-performance manifolds in the hyperparameter space. Control experiments on Erd\H{o}s-R\'enyi graphs show the phenomena persist beyond small-world topologies. Finally, our results show that $w_{\text{crit}}$ consistently falls within empirical high-performance regions, validating $w_{\text{crit}}$ as a robust starting coordinate for parameter search and fine-tuning. To ensure reproducibility, the full Python code is publicly available.