Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation
From MaRDI portal
Publication:2079548
DOI10.1016/j.jmaa.2022.126601OpenAlexW3177656875MaRDI QIDQ2079548
Adrian Riekert, Arnulf Jentzen
Publication date: 30 September 2022
Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2107.04479
Artificial intelligence (68Txx) Existence theories in calculus of variations and optimal control (49Jxx)
Related Items (1)
Uses Software
Cites Work
- \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
- Topological properties of the set of functions generated by neural networks of fixed size
- Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning
- Solving the Kolmogorov PDE by means of deep learning
- A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions
- Sparse optimization on measures with over-parameterized gradient descent
- Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions
- A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions
- A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Convergence of the Iterates of Descent Methods for Analytic Cost Functions
- Unnamed Item
- Unnamed Item
This page was built for publication: Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation
