372. A Gradient Method with Momentum for Riemannian Manifolds
Invited abstract in session WB-3: Recent Advances in Line-Search Based Optimization, stream Large scale optimization: methods and algorithms.
Wednesday, 10:30-12:30Room: B100/4011
Authors (first author is the speaker)
| 1. | Diego Scuppa
|
| Department of Computer, Control and Management Engineering, Sapienza University of Rome | |
| 2. | Filippo Leggio
|
| Department of Computer, Control and Management Engineering, Sapienza University of Rome | |
| 3. | Marco Sciandrone
|
| DIAG, Sapienza Università di Roma |
Abstract
In this work we consider smooth optimization problems on Rieman-
nian manifolds and we propose gradient methods with momentum.
Convergence results are established and computational experiments are
performed, on both academic tasks and real-world problems. The obtained computational results show the validity of the
proposed approach that extends that recently presented.
Keywords
- Linear and nonlinear optimization
- First-order optimization
- Large-scale optimization
Status: accepted
Back to the list of papers