Michael Köhler

On the rate of convergence of a neural network regression estimate learned by gradient descent

2019 · arXiv (Cornell University)

Nonparametric regression with random design is considered. Estimates are defined by minimzing a penalized empirical $L_2$ risk over a suitably chosen class of neural networks with one hidden layer via gradient descent. Here, the gradient …

Analysis of the Rate of Convergence of an Over-Parametrized Deep Neural Network Estimate Learned by Gradient Descent

2025 · IEEE Transactions on Information Theory

Estimation of a regression function from independent and identically distributed random variables is considered. The$L_{2}$error with integration with respect to the design measure is used as an error criterion. Over-parametrized deep neural network estimates are …