Picture for Johannes Schmidt-Hieber

Johannes Schmidt-Hieber

Understanding the Effect of GCN Convolutions in Regression Tasks

Add code
Oct 26, 2024
Viaarxiv icon

On the VC dimension of deep group convolutional neural networks

Add code
Oct 21, 2024
Viaarxiv icon

Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models

Add code
Sep 11, 2024
Viaarxiv icon

Convergence guarantees for forward gradient descent in the linear regression model

Add code
Sep 26, 2023
Viaarxiv icon

Dropout Regularization Versus $\ell_2$-Penalization in the Linear Model

Add code
Jun 18, 2023
Viaarxiv icon

Interpreting learning in biological neural networks as zero-order optimization method

Add code
Jan 27, 2023
Viaarxiv icon

On the inability of Gaussian process regression to optimally learn compositional functions

Add code
May 16, 2022
Viaarxiv icon

On generalization bounds for deep networks based on loss surface implicit regularization

Add code
Jan 12, 2022
Figure 1 for On generalization bounds for deep networks based on loss surface implicit regularization
Figure 2 for On generalization bounds for deep networks based on loss surface implicit regularization
Viaarxiv icon

Convergence rates of deep ReLU networks for multiclass classification

Add code
Aug 02, 2021
Figure 1 for Convergence rates of deep ReLU networks for multiclass classification
Figure 2 for Convergence rates of deep ReLU networks for multiclass classification
Viaarxiv icon

The Kolmogorov-Arnold representation theorem revisited

Add code
Jul 31, 2020
Figure 1 for The Kolmogorov-Arnold representation theorem revisited
Figure 2 for The Kolmogorov-Arnold representation theorem revisited
Viaarxiv icon