Convergence analysis for over-parameterized deep learning
From MaRDI portal
Rate of convergence, degree of approximation (41A25) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Artificial neural networks and deep learning (68T07)
Recommendations
Cites work
- A Rate of Convergence of Physics Informed Neural Networks for the Linear Second Order Elliptic PDEs
- Adaptive approximation and generalization of deep neural network with intrinsic dimensionality
- Approximation rates for neural networks with encodable weights in smoothness spaces
- Benign overfitting in linear regression
- Convergence rate analysis for deep Ritz method
- Deep learning: a statistical viewpoint
- Deep neural networks for estimation and inference
- Elliptic Partial Differential Equations of Second Order
- Error bounds for approximations with deep ReLU networks
- Estimates near the boundary for solutions of elliptic partial differential equations satisfying general boundary conditions. I
- Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs
- Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation
- Foundations of machine learning
- Just interpolate: kernel ``ridgeless regression can generalize
- Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
- Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
- Nonparametric regression using deep neural networks with ReLU activation function
- On deep learning as a remedy for the curse of dimensionality in nonparametric regression
- On the rate of convergence of fully connected deep neural network regression estimates
- Over-parametrized deep neural networks minimizing the empirical risk do not generalize well
- Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
- Reconciling modern machine-learning practice and the classical bias-variance trade-off
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
This page was built for publication: Convergence analysis for over-parameterized deep learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6608346)
