| Publication | Date of Publication | Type |
|---|
On the existence of infinitely many realization functions of non-global local minima for artificial neural networks with ReLU activation Discrete and Continuous Dynamical Systems. Series B | 2027-01-01 | Paper |
Algorithmically designed artificial neural networks (ADANNs): higher order deep operator learning for parametric partial differential equations Journal of Machine Learning | 2026-01-01 | Paper |
Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks SIAM/ASA Journal on Uncertainty Quantification | 2025-09-30 | Paper |
On the existence of global minima and convergence analyses for gradient descent methods in the training of deep neural networks Journal of Machine Learning | 2025-07-22 | Paper |
Convergence to good non-optimal critical points in the training of neural networks: Gradient descent optimization with one random initialization overcomes all bad non-global local minima with high probability (available as arXiv preprint) | 2025-01-01 | Paper |
Asymptotic stability properties and a priori bounds for Adam and other gradient descent optimization methods (available as arXiv preprint) | 2025-01-01 | Paper |
Strong overall error analysis for the training of artificial neural networks via random initializations Communications in Mathematics and Statistics | 2024-10-10 | Paper |
An Overview on Machine Learning Methods for Partial Differential Equations: from Physics Informed Neural Networks to Deep Operator Learning (available as arXiv preprint) | 2024-01-01 | Paper |
| A proof of the corrected Sister Beiter cyclotomic coefficient conjecture inspired by Zhao and Zhang | 2023-04-18 | Paper |
| Deep neural network approximation of composite functions without the curse of dimensionality | 2023-04-12 | Paper |
| Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations | 2023-02-07 | Paper |
Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations (available as arXiv preprint) | 2023-01-01 | Paper |
Deep neural network approximation of composite functions without the curse of dimensionality (available as arXiv preprint) | 2023-01-01 | Paper |
A proof of the corrected Sister Beiter cyclotomic coefficient conjecture inspired by Zhao and Zhang (available as arXiv preprint) | 2023-01-01 | Paper |
| Convergence to good non-optimal critical points in the training of neural networks: Gradient descent optimization with one random initialization overcomes all bad non-global local minima with high probability | 2022-12-26 | Paper |
Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation Journal of Mathematical Analysis and Applications | 2022-09-30 | Paper |
Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances Statistics & Probability Letters | 2022-08-30 | Paper |
A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions ZAMP. Zeitschrift für angewandte Mathematik und Physik | 2022-08-25 | Paper |
A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions Journal of Complexity | 2022-06-17 | Paper |
| On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation | 2022-02-23 | Paper |
On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation (available as arXiv preprint) | 2022-01-01 | Paper |
Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation (available as arXiv preprint) | 2021-07-09 | Paper |
A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions (available as arXiv preprint) | 2021-04-01 | Paper |