Bayes-optimal learning of deep random networks of extensive-width
From MaRDI portal
Cites work
- A random matrix approach to neural networks
- Asymptotics of representation learning in finite Bayesian neural networks*
- Bayesian interpolation with deep linear networks
- Deterministic equivalent and error universality of deep random features learning
- Generalization error of random feature and kernel methods: hypercontractivity and kernel matrix concentration
- Generalization performance of Bayes optimal classification algorithm for learning a perceptron
- Gibbs sampling the posterior of neural networks
- Learning a rule in a multilayer neural network
- Mean-field inference methods for neural networks
- Nonlinear random matrix theory for deep learning
- Optimal errors and phase transitions in high-dimensional generalized linear models
- Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
- Precise learning curves and higher-order scaling limits for dot-product kernel regression
- Spectrum estimation for large dimensional covariance matrices using random matrix theory
- Statistical Physics of Spin Glasses and Information Processing
- Surprises in high-dimensional ridgeless least squares interpolation
- The committee machine: computational to statistical gaps in learning a two-layers neural network
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
- The Nishimori line and Bayesian statistics
- The Parisi formula
- Universality Laws for High-Dimensional Learning With Random Features
- When do neural networks outperform kernel methods?*
- Wide neural networks of any depth evolve as linear models under gradient descent *
This page was built for publication: Bayes-optimal learning of deep random networks of extensive-width
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7233608)
