Johannes Schmidt-Hieber

29 papers A* 1A 1Journal 27

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Central limit theorems for the outputs of fully convolutional neural networks with time series input. CoRR Annika Betken, Giorgio Micali, Johannes Schmidt-Hieber
2026	J	`jnl`	Semi-Supervised Learning on Graphs using Graph Neural Networks. CoRR Juntong Chen, Claire Donnat, Olga Klopp, Johannes Schmidt-Hieber
2025	J	`jnl`	On the Universal Representation Property of Spiking Neural Networks. CoRR Shayan Hundrieser, Philipp Tuchel, Insung Kong, Johannes Schmidt-Hieber
2025	J	`jnl`	On the expressivity of deep Heaviside networks. CoRR Insung Kong, Juntong Chen, Sophie Langer, Johannes Schmidt-Hieber
2025	J	`jnl`	Spike-timing-dependent Hebbian learning as noisy gradient descent. CoRR Niklas Dexheimer, Sascha Gaudlitz, Johannes Schmidt-Hieber
2025	J	`jnl`	Statistical Guarantees for High-Dimensional Stochastic Gradient Descent. CoRR Jiaqi Li, Zhipeng Lou, Johannes Schmidt-Hieber, Wei Biao Wu
2025	J	`jnl`	Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization. CoRR Gabriel Clara, Sophie Langer, Johannes Schmidt-Hieber
2025	A	`conf`	Understanding the Effect of GCN Convolutions in Regression Tasks. AISTATS Juntong Chen, Johannes Schmidt-Hieber, Claire Donnat, Olga Klopp
2024	J	`jnl`	Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models. CoRR Jiaqi Li, Johannes Schmidt-Hieber, Wei Biao Wu
2024	J	`jnl`	Dropout Regularization Versus l2-Penalization in the Linear Model. J. Mach. Learn. Res. Gabriel Clara, Sophie Langer, Johannes Schmidt-Hieber
2024	J	`jnl`	Improving the Convergence Rates of Forward Gradient Descent with Repeated Sampling. CoRR Niklas Dexheimer, Johannes Schmidt-Hieber
2024	J	`jnl`	On the VC dimension of deep group convolutional neural networks. CoRR Anna Sepliarskaia, Sophie Langer, Johannes Schmidt-Hieber
2024	J	`jnl`	Understanding the Effect of GCN Convolutions in Regression Tasks. CoRR Juntong Chen, Johannes Schmidt-Hieber, Claire Donnat, Olga Klopp
2023	J	`jnl`	Codivergences and information matrices. CoRR Alexis Derumigny, Johannes Schmidt-Hieber
2023	J	`jnl`	Convergence guarantees for forward gradient descent in the linear regression model. CoRR Thijs Bos, Johannes Schmidt-Hieber
2023	J	`jnl`	Hebbian learning inspired estimation of the linear regression parameters from queries. CoRR Johannes Schmidt-Hieber, Wouter M. Koolen
2023	J	`jnl`	Interpreting learning in biological neural networks as zero-order optimization method. CoRR Johannes Schmidt-Hieber
2023	J	`jnl`	On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization. IEEE Trans. Inf. Theory Masaaki Imaizumi, Johannes Schmidt-Hieber
2023	J	`jnl`	Posterior Contraction for Deep Gaussian Process Priors. J. Mach. Learn. Res. Gianluca Finocchio, Johannes Schmidt-Hieber
2022	J	`jnl`	On generalization bounds for deep networks based on loss surface implicit regularization. CoRR Masaaki Imaizumi, Johannes Schmidt-Hieber
2022	A*	`conf`	On the inability of Gaussian process regression to optimally learn compositional functions. NeurIPS Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
2022	J	`jnl`	On the inability of Gaussian process regression to optimally learn compositional functions. CoRR Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
2021	J	`jnl`	Convergence rates of deep ReLU networks for multiclass classification. CoRR Thijs Bos, Johannes Schmidt-Hieber
2021	J	`jnl`	The Kolmogorov-Arnold representation theorem revisited. Neural Networks Johannes Schmidt-Hieber
2020	J	`jnl`	The Kolmogorov-Arnold representation theorem revisited. CoRR Johannes Schmidt-Hieber
2019	J	`jnl`	A comparison of deep networks with ReLU activation function and linear spline-type methods. Neural Networks Konstantin Eckle, Johannes Schmidt-Hieber
2019	J	`jnl`	Deep ReLU network approximation of functions on a manifold. CoRR Johannes Schmidt-Hieber
2018	J	`jnl`	A comparison of deep networks with ReLU activation function and linear spline-type methods. CoRR Konstantin Eckle, Johannes Schmidt-Hieber
2017	J	`jnl`	Nonparametric regression using deep neural networks with ReLU activation function. CoRR Johannes Schmidt-Hieber