The authors introduce retraction-based and projection-based Riemannian Bregman gradient methods with O(1/epsilon^2) iteration complexity and stochastic variants with O(1/epsilon^4) sample complexity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On Relatively Smooth Optimization over Riemannian Manifolds
The authors introduce retraction-based and projection-based Riemannian Bregman gradient methods with O(1/epsilon^2) iteration complexity and stochastic variants with O(1/epsilon^4) sample complexity.