Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spaces

6 April 2021

Papers citing "Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spaces"

8 / 8 papers shown

Title
High-dimensional classification problems with Barron regular boundaries under margin conditions Jonathan García Philipp Petersen 74 1 0 10 Dec 2024
Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations Arnulf Jentzen Adrian Riekert Philippe von Wurstemberger 29 1 0 07 Feb 2023
Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$ R. Gentile G. Welper ODL 52 6 0 17 Sep 2022
Constrained Few-Shot Learning: Human-Like Low Sample Complexity Learning and Non-Episodic Text Classification Jaron Mar Jiamou Liu 30 1 0 17 Aug 2022
Learning ReLU networks to high uniform accuracy is intractable Julius Berner Philipp Grohs F. Voigtlaender 32 4 0 26 May 2022
Sobolev-type embeddings for neural network approximation spaces Philipp Grohs F. Voigtlaender 16 1 0 28 Oct 2021
Deep neural network solution of the electronic Schrödinger equation J. Hermann Zeno Schätzle Frank Noé 149 446 0 16 Sep 2019
Benefits of depth in neural networks Matus Telgarsky 148 602 0 14 Feb 2016