Michael Kohler

collaborators

2 papers

math.ST2025

On the rate of convergence of an over-parametrized deep neural network regression estimate learned by gradient descent

Michael Kohler

Nonparametric regression with random design is considered. The $L_{2}$ error with integration with respect to the design measure is used as the error criterion. An over-parametrized…

stat.ML2023

Analysis of the expected $L_{2}$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization

Selina Drews, Michael Kohler

Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L_{2}$ risk are universally cons…

On the rate of convergence of an over-parametrized deep neural network regression estimate learned by gradient descent

Analysis of the expected L2​ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization

Analysis of the expected $L_{2}$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization