Riemannian conditional gradient methods are introduced for composite optimization on manifolds, achieving O(1/k) convergence for adaptive and diminishing steps and O(1/ε²) iteration complexity for Armijo steps.
Journal of Machine Learning Research 18(144), 1–46 (2017)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Riemannian conditional gradient methods for composite optimization problems
Riemannian conditional gradient methods are introduced for composite optimization on manifolds, achieving O(1/k) convergence for adaptive and diminishing steps and O(1/ε²) iteration complexity for Armijo steps.