Gaussian and non-Gaussian universality of data augmentation
From MaRDI portal
Cites work
- 10.1162/153244302760200704
- A generalization of the Lindeberg principle
- Anisotropic local laws for random matrices
- Applications of the Lindeberg Principle in Communications and Statistical Learning
- Bagging predictors
- Black-box tests for algorithmic stability
- scientific article; zbMATH DE number 3567657 (Why is no real title available?)
- scientific article; zbMATH DE number 7306924 (Why is no real title available?)
- scientific article; zbMATH DE number 3244317 (Why is no real title available?)
- Invariance principles for homogeneous sums of free random variables
- Limit theorems for distributions invariant under groups of transformations
- Limit Theorems for Multilinear Forms and Quasipolynomial Functions
- Limit theorems for polylinear forms
- Marchenko–Pastur law with relaxed independence conditions
- Neural collapse with unconstrained features
- Noise stability of functions with low influences: invariance and optimality
- On upper and lower bounds for the variance of a function of a random variable
- Random matrices: universality of local eigenvalue statistics
- Surprises in high-dimensional ridgeless least squares interpolation
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
- The spectrum of heavy tailed random matrices
- Total variation distance between stochastic polynomials and invariance principles
- Universality Laws for High-Dimensional Learning With Random Features
- Universality of approximate message passing with semirandom matrices
- Universality of covariance matrices
- Universality of regularized regression estimators in high dimensions
This page was built for publication: Gaussian and non-Gaussian universality of data augmentation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7442252)