prof.dr. A.J. Schmidt-Hieber (Johannes)

Johannes Schmidt-Hieber is hoogleraar statistiek op de Universiteit Twente. Link naar persoonlijke webpagina

Mathematics

# Activation Function
# Contraction
# Gaussian Process
# Neural Networks
# Nonparametric Regression
# Recovery

Business & Economics

# Bayesian Analysis
# Nonparametric Regression

Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), Mathematics of Operations Research (MOR)

Derumigny, A. , & Schmidt-Hieber, A. J. (2023). On lower bounds for the bias-variance trade-off. Annals of the Institute of Statistical Mathematics, 51(4), 1510 - 1533. https://doi.org/10.1214/23-AOS2279

Imaizumi, M. , & Schmidt-Hieber, A. J. (2023). On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization. IEEE transactions on information theory, 69(2), 1203- 1223. https://doi.org/10.1109/TIT.2022.3215088

Finocchio, G. , & Schmidt-Hieber, A. J. (2023). Posterior Contraction for Deep Gaussian Process Priors. Journal of machine learning research, 24(66), 1-49. https://jmlr.org/papers/volume24/21-0556/21-0556.pdf

Schmidt-Hieber, J. , & Zamolodtchikov, P. (2022). Local convergence rates of the least squares estimator with applications to transfer learning. ArXiv.org. https://doi.org/10.48550/arXiv.2204.05003

Bos, T. , & Schmidt-Hieber, A. J. (2022). Convergence rates of deep ReLU networks for multiclass classification. Electronic Journal of Statistics, 16(1), 2724 - 2773. https://doi.org/10.1214/22-EJS2011

Schmidt-Hieber, A. J., Schneider, L., Staudt, T., Krajina, A., Aspelmeier, T., & Munk, A. (2021). Posterior analysis of n in the binomial (n,p) problem with both parameters unknown—with applications to quantitative nanoscopy. Annals of statistics, 49(6), 3534-3558. https://doi.org/10.1214/21-AOS2096

Finocchio, G. (2021). Two perspectives on high-dimensional estimation problems: posterior contraction and median-of-means. [PhD Thesis - Research UT, graduation UT, University of Twente]. University of Twente. https://doi.org/10.3990/1.9789036552356

Schmidt-Hieber, A. J. (2021). The Kolmogorov–Arnold representation theorem revisited. Neural networks, 137, 119-126. https://doi.org/10.1016/j.neunet.2021.01.020

Finocchio, G. , & Schmidt-Hieber, A. J. (2021). Posterior contraction for deep Gaussian process priors. https://arxiv.org/abs/2105.07410

Langer, S. (2020). Ein Beitrag zur Statistischen Theorie des Deep Learnings. [PhD Thesis - Research external, graduation external, Technische Universitat Darmstadt]. Verlag Dr. Hut.

Reiss, M. , & Schmidt-Hieber, J. (2020). Posterior contraction rates for support boundary recovery. Stochastic processes and their applications, 130(11), 6638. https://doi.org/10.1016/j.spa.2020.06.005

Schmidt-Hieber, A. J. (2020). Nonparametric regression using deep neural networks with ReLU activation function. Annals of statistics, 48(4), 1875-1897. https://doi.org/10.1214/19-AOS1875

Schmidt-Hieber, A. J. (2020). Rejoinder: “Nonparametric regression using deep neural networks with ReLU activation function”. Annals of statistics, 48(4), 1916-1921. https://doi.org/10.1214/19-AOS1931

Reiss, M. , & Schmidt-Hieber, A. J. (2020). Nonparametric Bayesian analysis of the compound Poisson prior for support boundary recovery. Annals of statistics, 48(3), 1432-1451. https://doi.org/10.1214/19-AOS1853

Derumigny, A. , & Schmidt-Hieber, J. (2020). On lower bounds for the bias-variance trade-off. ArXiv.org. https://arxiv.org/abs/2006.00278

Finocchio, G. , & Schmidt-Hieber, J. (2020). Bayesian variance estimation in the Gaussian sequence model with partial information on the means. Electronic Journal of Statistics, 14(1), 239-271. https://doi.org/10.1214/19-EJS1671

Eckle, K. , & Schmidt-Hieber, A. J. (2019). A comparison of deep networks with ReLU activation function and linear spline-type methods. Neural networks, 110, 232-242. https://doi.org/10.1016/j.neunet.2018.11.005

Dunker, F., Eckle, K. , Proksch, K. , & Schmidt-Hieber, A. J. (2019). Tests for qualitative features in the random coefficients model. Electronic Journal of Statistics, 13(2), 2257-2306. https://doi.org/10.1214/19-EJS1570

Bekijk alle publicaties van deze medewerker

Vakken in het huidig collegejaar worden toegevoegd op het moment dat zij definitief zijn in het Osiris systeem. Daarom kan het zijn dat de lijst nog niet compleet is voor het gehele collegejaar.

+31534896958

+31534894272 (secretaresse)

a.j.schmidt-hieber@utwente.nl

Bezoekadres

Universiteit Twente
Faculty of Electrical Engineering, Mathematics and Computer Science
Zilverling (gebouwnr. 11), kamer 2057
Hallenweg 19
7522NH Enschede

Navigeer naar locatie

Postadres

Universiteit Twente
Faculty of Electrical Engineering, Mathematics and Computer Science
Zilverling 2057
Postbus 217
7500 AE Enschede

Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS), Mathematics of Operations Research (MOR)

Universiteit Twente Drienerlolaan 5
7522 NB Enschede

+31 (0)53 489 9111
info@utwente.nl
Route

Welkom...

prof.dr. A.J. Schmidt-Hieber (Johannes)

Hoogleraar

Over mij

Expertises

Verbonden aan

Publicaties

Pure Link

Vakken Collegejaar 2023/2024

Vakken Collegejaar 2022/2023

Contactgegevens

Bezoekadres

Postadres

Verbonden aan