Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks

Ridge regression; shrinkage estimators (Lasso) (62J07) Artificial neural networks and deep learning (68T07) Random matrices (probabilistic aspects) (60B20)

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Strong convergence of ESD for the generalized sample covariance matrices when \(p/n \rightarrow 0\)
Testing the sphericity of a covariance matrix when the dimension is much larger than the sample size
User-friendly tail bounds for sums of random matrices
Hanson-Wright inequality and sub-Gaussian concentration
A note on the Hanson-Wright inequality for random vectors with dependencies
The limiting spectral distribution of the product of the Wigner matrix and a nonnegative definite matrix
Spectral analysis of large dimensional random matrices
The smallest eigenvalue of a large dimensional Wishart matrix
Convergence to the semicircle law
A random matrix approach to neural networks
Convergence of the largest eigenvalue of normalized sample covariance matrices when \(p\) and \(n\) both tend to infinity with their ratio converging to zero
Limiting spectral distribution of normalized sample covariance matrices with \(p/n\to 0\)
Eigenvalue distribution of some nonlinear models of random matrices
The interpolation phase transition in neural networks: memorization and generalization under lazy training
Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration
Just interpolate: kernel ``ridgeless regression can generalize
A note on the Pennington-Worah distribution
CLT for linear spectral statistics of normalized sample covariance matrices with the dimension much larger than the sample size
Limiting spectral distribution of renormalized separable sample covariance matrices when \(p/n\to 0\)
Asymptotic freeness of layerwise Jacobians caused by invariance of multilayer perceptron: the Haar orthogonal case
PARTIAL TRANSPOSITION OF RANDOM STATES AND NON-CENTERED SEMICIRCULAR DISTRIBUTIONS
The PPT square conjecture holds generically for some classes of independent states
Lectures on the Combinatorics of Free Probability
High-Dimensional Probability
Learning curves of generic features maps for realistic datasets with a teacher-student model*
The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
Alice and Bob Meet Banach
On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions
A Bound on Tail Probabilities for Quadratic Forms in Independent Random Variables
An Inverse Matrix Adjustment Arising in Discriminant Analysis
Deep learning: a statistical viewpoint
Large-dimensional random matrix theory and its applications in deep learning and wireless communications
Spiked singular values and vectors under extreme aspect ratios
Asymptotic normality for eigenvalue statistics of a general sample covariance matrix when \(p/n \to \infty\) and applications
Universality Laws for High-Dimensional Learning With Random Features

This page was built for publication: Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks