Riemannian Optimization via Frank-Wolfe Methods
Abstract We study projection-free methods for constrained Riemannian optimization. In particular, we propose a Riemannian Frank-Wolfe (RFW) method that handles constraints directly, in contrast to prior methods that rely on (potentially costly) projections. We analyze non-asymptotic convergence rate...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC,
2022-07-18T15:51:41Z.
|
| Subjects: | |
| Online Access: | Get fulltext |