Research map / Learning theory and algorithms / Kernels and regression theory
The Asymptotic Performance of Linear Echo State Neural Networks
Romain Couillet, Gilles Wainrib, Harry Sevi, Hafiz Tiomoko Ali
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use a non-normal (i.i.d. Gaussian) connectivity matrix instead of a normal Wigner matrix | Linear ESN · Memory curve, c=0.5 | MC(tau=4): 5.7e-5 -> 3.9e-2 | Improved |
| Use a non-normal (i.i.d. Gaussian) connectivity matrix instead of a normal Wigner matrix | Linear ESN · Memory curve, c=0.5 | MC(tau=1): 1.6e-2 -> 2.0e-1 | Improved |
| Use a non-normal (i.i.d. Gaussian) connectivity matrix instead of Wigner on PM10 one-day-ahead task | Linear ESN · PM10 one-step ahead | testing NMSE | Improved |
| Use multi-memory connectivity matrix instead of a single-rate Haar matrix with ill-chosen sigma | Linear ESN · Mackey-Glass one-step ahead | testing NMSE | Improved |
| Increase in-network noise variance eta^2 when test inputs have impulsive noise | Linear ESN · Mackey-Glass one-step ahead with 1% or 10% impulsive noise | testing NMSE | Improved |
| Decrease in-network noise variance eta^2 | Linear ESN · Testing NMSE variance across testbeds | std of testing NMSE | Mixed |
Closest papers by meaning
- A Random Matrix Approach to Echo-State Neural Networks (ICML 2016 · similarity 0.90)
- Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity (ICML 2025 · similarity 0.82)
- Bayes-optimal learning of an extensive-width neural network from quadratically many samples (NeurIPS 2024 · similarity 0.81)
- Frequency Domain Reservoir Computing (NeurIPS 2026 · similarity 0.81)
- Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs (ICML 2025 · similarity 0.81)
- The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks (NeurIPS 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
