A projection-based zeroth-order federated learning algorithm on Riemannian manifolds achieves sublinear convergence with linear speedup, using only Euclidean random perturbations.
Zeroth-order Riemannian Averaging Stochastic Approximation Algorithms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present Zeroth-order Riemannian Averaging Stochastic Approximation (\texttt{Zo-RASA}) algorithms for stochastic optimization on Riemannian manifolds. We show that \texttt{Zo-RASA} achieves optimal sample complexities for generating $\epsilon$-approximation first-order stationary solutions using only one-sample or constant-order batches in each iteration. Our approach employs Riemannian moving-average stochastic gradient estimators, and a novel Riemannian-Lyapunov analysis technique for convergence analysis. We improve the algorithm's practicality by using retractions and vector transport, instead of exponential mappings and parallel transports, thereby reducing per-iteration complexity. Additionally, we introduce a novel geometric condition, satisfied by manifolds with bounded second fundamental form, which enables new error bounds for approximating parallel transport with vector transport.
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated Learning on Riemannian Manifolds: A Gradient-Free Projection-Based Approach
A projection-based zeroth-order federated learning algorithm on Riemannian manifolds achieves sublinear convergence with linear speedup, using only Euclidean random perturbations.