Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks
Sudip Laudari, Puspa Raj Adhikari
cs.LG, cs.AI, math.DS
Submitted: 2026-08-05
Comments: 18 pages, 6 figures
Code: https://github.com/Laudarisd/dmp_esn
License: http://creativecommons.org/licenses/by/4.0/
The gist: Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant.
Terminology
Abstract
Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant. Existing pruning methods largely rely on static connectivity or activation statistics, which may overlook neurons that shape input-driven state transitions. We propose Dynamical Mode Pruning (DMP), a reservoir pruning method that ranks neurons by their contribution to dominant transition modes obtained from a trajectory-averaged Jacobian Gramian. DMP removes low-impact units and retrains only the readout. Experiments on chaotic and real-world time-series benchmarks show that DMP improves or preserves forecasting accuracy while reducing redundant reservoir components. Our results suggest that dynamical influence is a useful criterion for reservoir refinement beyond static structural importance alone.
Sources
- Chasing the Echo State Property
- Feature-Based Echo-State Networks: A Step Towards Interpretability and Minimalism in Reservoir Computer
- Centrality-Based Pruning for Efficient Echo State Networks
- One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks