Full error analysis for the training of deep neural networks

30 September 2019

Papers citing "Full error analysis for the training of deep neural networks"

15 / 15 papers shown

Title
Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks Arnulf Jentzen Adrian Riekert 41 4 0 07 Feb 2024
Deep neural network approximation of composite functions without the curse of dimensionality Adrian Riekert 26 0 0 12 Apr 2023
Error analysis for deep neural network approximations of parametric hyperbolic conservation laws Tim De Ryck Siddhartha Mishra PINN 15 10 0 15 Jul 2022
Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions Martin Hutzenthaler Arnulf Jentzen Katharina Pohl Adrian Riekert Luca Scarpa MLT 34 6 0 13 Dec 2021
Deep Network Approximation in Terms of Intrinsic Parameters Zuowei Shen Haizhao Yang Shijun Zhang 21 9 0 15 Nov 2021
Polynomial-Spline Neural Networks with Exact Integrals Jonas A. Actor Andrew Huang N. Trask 28 1 0 26 Oct 2021
On the approximation of functions by tanh neural networks Tim De Ryck S. Lanthaler Siddhartha Mishra 26 138 0 18 Apr 2021
A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions Arnulf Jentzen Adrian Riekert MLT 34 13 0 01 Apr 2021
Convergence rates for gradient descent in the training of overparameterized artificial neural networks with biases Arnulf Jentzen T. Kröger ODL 28 7 0 23 Feb 2021
Partition of unity networks: deep hp-approximation Kookjin Lee N. Trask Ravi G. Patel Mamikon A. Gulian E. Cyr 22 30 0 27 Jan 2021
Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data Ben Adcock Simone Brugiapaglia N. Dexter S. Moraga 36 29 0 11 Dec 2020
Non-convergence of stochastic gradient descent in the training of deep neural networks Patrick Cheridito Arnulf Jentzen Florian Rossmannek 14 37 0 12 Jun 2020
Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation Arnulf Jentzen Timo Welti 22 15 0 03 Mar 2020
Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis Côme Huré H. Pham Achref Bachouch N. Langrené 13 64 0 11 Dec 2018
Solving the Kolmogorov PDE by means of deep learning C. Beck S. Becker Philipp Grohs Nor Jaafari Arnulf Jentzen 19 91 0 01 Jun 2018