Convergence analysis for over-parameterized deep learning

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Artificial neural networks and deep learning (68T07) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Rate of convergence, degree of approximation (41A25)

Cites Work

Unnamed Item
Unnamed Item
The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
Over-parametrized deep neural networks minimizing the empirical risk do not generalize well
On the rate of convergence of fully connected deep neural network regression estimates
Approximation rates for neural networks with encodable weights in smoothness spaces
Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
Just interpolate: kernel ``ridgeless regression can generalize
Nonparametric regression using deep neural networks with ReLU activation function
Error bounds for approximations with deep ReLU networks
On deep learning as a remedy for the curse of dimensionality in nonparametric regression
Estimates near the boundary for solutions of elliptic partial differential equations satisfying general boundary conditions. I
Elliptic Partial Differential Equations of Second Order
Deep Neural Networks for Estimation and Inference
Benign overfitting in linear regression
Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs
Convergence Rate Analysis for Deep Ritz Method
A Rate of Convergence of Physics Informed Neural Networks for the Linear Second Order Elliptic PDEs
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
Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
Deep learning: a statistical viewpoint
Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation

This page was built for publication: Convergence analysis for over-parameterized deep learning