Gradient descent for deep neural network learning (A01)

• Subject Area: Mathematics
• Term: since 2022
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 442047500

This project aims at making progress in the understanding of convergence properties of (stochastic) gradient descent methods for training deep neural networks. We target several extensions of initial results by the PIs on (fully connected) linear networks. For instance,we will investigate convergence to global minimizers for training structured linear neural networks and nonlinear neural networks. An important aspect of the project will be to explore the Riemannian geometry underlying the corresponding gradient flows.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1481: Sparsity and Singular Structures
• Applicant Institution: Rheinisch-Westfälische Technische Hochschule Aachen
• Project Heads: Professor Dr. Holger Rauhut; Professor Dr. Michael Westdickenberg