Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation

Jentzen A, Riekert A (2023)
In: Journal of Mathematical Analysis and Applications, 517(2)
Type of Publication: Research article (journal)

Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation

Eberle, Simon; Jentzen, Arnulf; Riekert, Adrian; Weiss, Georg S. (2023)
In: Electronic Research Archive, 31(5)
Type of Publication: Research article (journal)

A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target…

Jentzen, Arnulf; Riekert, Adrian (2022)
In: Journal of Machine Learning Research, 23(260)
Type of Publication: Research article (journal)

A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions

Cheridito, Patrick; Jentzen, Arnulf; Riekert, Adrian; Rossmannek, Florian (2022)
In: Journal of Complexity, 72
Type of Publication: Research article (journal)

On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation

Ibragimov, Shokhrukh; Jentzen, Arnulf; Kröger, Timo; Riekert, Adrian (2022)
In: ArXiv:2202.11481.
Type of Publication: Research article in digital collection

Publications

Contact

Top-Links

Strong overall error analysis for the training of artificial neural networks via random initializations Jentzen A, Riekert A (2023) In: Communications in Mathematics and Statistics, 0 Type of Publication: Research article (journal)
Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation Jentzen A, Riekert A (2023) In: Journal of Mathematical Analysis and Applications, 517(2) Type of Publication: Research article (journal)
Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations Jentzen, A.; Riekert, A.; von Wurstemberger, P. (2023) In: arXiv.org:2302.03286. Type of Publication: Research article in digital collection
Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation Eberle, Simon; Jentzen, Arnulf; Riekert, Adrian; Weiss, Georg S. (2023) In: Electronic Research Archive, 31(5) Type of Publication: Research article (journal)
On the existence of global minima and convergence analyses for gradient descent methods in the training of deep neural networks Jentzen A, Riekert A (2022) In: Journal of Machine Learning, 1(2) Type of Publication: Research article (journal)
A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target… Jentzen, Arnulf; Riekert, Adrian (2022) In: Journal of Machine Learning Research, 23(260) Type of Publication: Research article (journal)
A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions Jentzen, Arnulf; Riekert, Adrian (2022) In: Zeitschrift für Angewandte Mathematik und Physik, 73(5) Type of Publication: Research article (journal)
A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions Cheridito, Patrick; Jentzen, Arnulf; Riekert, Adrian; Rossmannek, Florian (2022) In: Journal of Complexity, 72 Type of Publication: Research article (journal)
Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances Riekert, Adrian (2022) In: Statistics and Probability Letters, 189 Type of Publication: Research article (journal)
On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation Ibragimov, Shokhrukh; Jentzen, Arnulf; Kröger, Timo; Riekert, Adrian (2022) In: ArXiv:2202.11481. Type of Publication: Research article in digital collection