The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality

DOI10.1613/JAIR.1.13547MaRDI QIDQ5043561zbMATH OpenOpenAlexFDO

Authors Vincent Froese, Christoph Hertrich, Rolf Niedermeier

Publication date 6 October 2022

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2105.08675

zbMATH Keywords

neural networks machine learning mathematical foundations

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• Complexity of training ReLU neural network
• Facets of neural network complexity
• Deep ReLU neural networks in high-dimensional approximation
• On size-independent sample complexity of ReLU networks
• Principled deep neural network training through linear programming

Cited in

(7)

• Principled deep neural network training through linear programming
• ReLU neural networks of polynomial size for exact maximum flow computation
• Towards Lower Bounds on the Depth of ReLU Neural Networks
• Magnitude and angle dynamics in training single ReLU neurons
• Neural networks with linear threshold activations: structure and algorithms
• Facets of neural network complexity
• A universal uniform approximation theorem for neural networks

This page was built for publication: The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5043561)