Johannes Schmidt-Hieber

Publication Activity (10 Years)

Years Active: 2017-2023
Publications (10 Years): 16

Top Topics

Linear Regression

Hebbian Learning

Convergence Rate

Gaussian Process

Top Venues

Neural Networks

IEEE Trans. Inf. Theory

J. Mach. Learn. Res.

Publications

Thijs Bos, Johannes Schmidt-Hieber
Convergence guarantees for forward gradient descent in the linear regression model. CoRR (2023)
Alexis Derumigny, Johannes Schmidt-Hieber
Codivergences and information matrices. CoRR (2023)
Gianluca Finocchio, Johannes Schmidt-Hieber
Posterior Contraction for Deep Gaussian Process Priors. J. Mach. Learn. Res. 24 (2023)
Masaaki Imaizumi, Johannes Schmidt-Hieber
On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization. IEEE Trans. Inf. Theory 69 (2) (2023)
Johannes Schmidt-Hieber
Interpreting learning in biological neural networks as zero-order optimization method. CoRR (2023)
Johannes Schmidt-Hieber, Wouter M. Koolen
Hebbian learning inspired estimation of the linear regression parameters from queries. CoRR (2023)
Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
On the inability of Gaussian process regression to optimally learn compositional functions. CoRR (2022)
Masaaki Imaizumi, Johannes Schmidt-Hieber
On generalization bounds for deep networks based on loss surface implicit regularization. CoRR (2022)
Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
On the inability of Gaussian process regression to optimally learn compositional functions. NeurIPS (2022)
Johannes Schmidt-Hieber
The Kolmogorov-Arnold representation theorem revisited. Neural Networks 137 (2021)
Thijs Bos, Johannes Schmidt-Hieber
Convergence rates of deep ReLU networks for multiclass classification. CoRR (2021)
Johannes Schmidt-Hieber
The Kolmogorov-Arnold representation theorem revisited. CoRR (2020)
Johannes Schmidt-Hieber
Deep ReLU network approximation of functions on a manifold. CoRR (2019)
Konstantin Eckle, Johannes Schmidt-Hieber
A comparison of deep networks with ReLU activation function and linear spline-type methods. Neural Networks 110 (2019)
Konstantin Eckle, Johannes Schmidt-Hieber
A comparison of deep networks with ReLU activation function and linear spline-type methods. CoRR (2018)
Johannes Schmidt-Hieber
Nonparametric regression using deep neural networks with ReLU activation function. CoRR (2017)