A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
From MaRDI portal
Publication:5020045
Recommendations
Cites work
- A model of double descent for high-dimensional binary linear classification
- A random matrix approach to neural networks
- Benign overfitting in linear regression
- Deterministic equivalents for certain functionals of large random matrices
- High-dimensional asymptotics of prediction: ridge regression and classification
- High-dimensional dynamics of generalization error in neural networks
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- Information, Physics, and Computation
- Just interpolate: kernel ``ridgeless regression can generalize
- On Random Matrices Arising in Deep Neural Networks. Gaussian Case
- On the equivalence between kernel quadrature rules and random feature expansions
- Random matrix methods for wireless communications.
- Reconciling modern machine-learning practice and the classical bias-variance trade-off
- Rigorous learning curve bounds from statistical mechanics
- Statistical mechanics of learning
- The elements of statistical learning. Data mining, inference, and prediction
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
Cited in
(11)- scientific article; zbMATH DE number 7255176 (Why is no real title available?)
- Towards a unified analysis of random Fourier features
- Binary classification of Gaussian mixtures: abundance of support vectors, benign overfitting, and regularization
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
- Breaking the waves: asymmetric random periodic features for low-bitrate kernel machines
- Benign Overfitting and Noisy Features
- Precise learning curves and higher-order scaling limits for dot-product kernel regression
- Conditioning of random Fourier feature matrices: double descent and generalization error
- Dyson equation for correlated linearizations and test error of random features regression
- Homogenization of SGD in high-dimensions: exact dynamics and generalization properties
- Modeling structured data learning with restricted Boltzmann machines in the teacher-student setting
This page was built for publication: A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5020045)
