Image de couverture de livre

A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Moakher, Yessin, Tiomoko, Malik, Louart, Cosme, Liao, Zhenyu
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Statistics Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Generalization in Representation Models via Random Matrix Theory: Application to Recurrent Networks
par: Moakher, Yessin, et autres
Publié: (2025)

Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization
par: Yaakoubi, Chiheb, et autres
Publié: (2026)

Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
par: Ilbert, Romain, et autres
Publié: (2024)

Optimal Bias-variance Tradeoff in Matrix and Tensor Estimation
par: Kumar, Shivam, et autres
Publié: (2025)

Precise Asymptotics and Refined Regret of Variance-Aware UCB
par: Fan, Yingying, et autres
Publié: (2024)

Random Forests as Statistical Procedures: Design, Variance, and Dependence
par: O'Connell, Nathaniel S.
Publié: (2026)

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
par: Dandi, Yatin, et autres
Publié: (2024)

Precise Asymptotics of Bagging Regularized M-estimators
par: Koriyama, Takuya, et autres
Publié: (2024)

The Benefits of Balance: From Information Projections to Variance Reduction
par: Liu, Lang, et autres
Publié: (2024)

High-Dimensional Analysis of Bootstrap Ensemble Classifiers
par: Tiomoko, Malik, et autres
Publié: (2025)

Optimal Ridge Regularization for Out-of-Distribution Prediction
par: Patil, Pratik, et autres
Publié: (2024)

Estimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance Reduction
par: Byambadalai, Undral, et autres
Publié: (2024)

Universal concentration for sums under arbitrary dependence
par: Louart, Cosme, et autres
Publié: (2026)

Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation
par: Morisset, Lucas, et autres
Publié: (2025)

UTICA: Multi-Objective Self-Distllation Foundation Model Pretraining for Time Series Classification
par: Moakher, Yessin, et autres
Publié: (2026)

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
par: Boudart, Pierre, et autres
Publié: (2026)

Resolvent convergence for sample covariance matrices with general covariance profiles and quadratic-form control
par: Louart, Cosme
Publié: (2021)

Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
par: Coeurdoux, Florentin, et autres
Publié: (2026)

Variance estimation in graphs with the fused lasso
par: Padilla, Oscar Hernan Madrid
Publié: (2022)

Variance Reduction for the Independent Metropolis Sampler
par: Liu, Siran, et autres
Publié: (2024)

CARE: Large Precision Matrix Estimation for Compositional Data
par: Zhang, Shucong, et autres
Publié: (2023)

Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
par: Morisset, Lucas, et autres
Publié: (2026)

On the Variance, Admissibility, and Stability of Empirical Risk Minimization
par: Kur, Gil, et autres
Publié: (2023)

Variance-Aware Estimation of Kernel Mean Embedding
par: Wolfer, Geoffrey, et autres
Publié: (2022)

Adaptive Split Balancing for Optimal Random Forest
par: Zhang, Yuqian, et autres
Publié: (2024)

Orthogonal Approximate Message Passing with Optimal Spectral Initializations for Rectangular Spiked Matrix Models
par: Chen, Haohua, et autres
Publié: (2025)

Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning
par: Dang, Hien, et autres
Publié: (2026)

On the Interpolation Error of Nonlinear Attention versus Linear Regression
par: Liao, Zhenyu, et autres
Publié: (2025)

Precise analysis of ridge interpolators under heavy correlations -- a Random Duality Theory view
par: Stojnic, Mihailo
Publié: (2024)

Jackknife Variance Estimation for Hájek-Dominated Generalized U-Statistics
par: Juergens, Jakob R.
Publié: (2025)

Fixed-Confidence Best Arm Identification with Decreasing Variance
par: Roychowdhury, Tamojeet, et autres
Publié: (2025)

Locally Optimal Fixed-Budget Best Arm Identification in Two-Armed Gaussian Bandits with Unknown Variances
par: Kato, Masahiro
Publié: (2023)

Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
par: Zhang, Yihan, et autres
Publié: (2024)

Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery
par: Kovačević, Filip, et autres
Publié: (2025)

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
par: Ji, Kaixuan, et autres
Publié: (2026)

Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon
par: Yu, Hao
Publié: (2025)

Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models
par: Moniri, Behrad, et autres
Publié: (2024)

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
par: Firdoussi, Aymane El, et autres
Publié: (2024)

Optimality of Approximate Message Passing Algorithms for Spiked Matrix Models with Rotationally Invariant Noise
par: Dudeja, Rishabh, et autres
Publié: (2024)

Bias-Corrected Joint Spectral Embedding for Multilayer Networks with Invariant Subspace: Entrywise Eigenvector Perturbation and Inference
par: Xie, Fangzheng
Publié: (2024)