MOLE

The project MOLE (Manifold Optimization and LEarning) aims at developing and analyzing new numerical algorithms to solve nonlinear tensor least-squares problems and to train deep neural networks on low-parametric Riemannian manifolds. The project is a collaboration with University of Florence and GSSI.

It has been financed in the PRIN2022 program by the Italian Minister for University, and is bound to start on February, 4 2025.

Further details will appear on this page after the project starts.