REVIEW 2 cited by
Federated Learning on Riemannian Manifolds
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Federated learning (FL) has found many important applications in smart-phone-APP based machine learning applications. Although many algorithms have been studied for FL, to the best of our knowledge, algorithms for FL with nonconvex constraints have not been studied. This paper studies FL over Riemannian manifolds, which finds important applications such as federated PCA and federated kPCA. We propose a Riemannian federated SVRG (RFedSVRG) method to solve federated optimization over Riemannian manifolds. We analyze its convergence rate under different scenarios. Numerical experiments are conducted to compare RFedSVRG with the Riemannian counterparts of FedAvg and FedProx. We observed from the numerical experiments that the advantages of RFedSVRG are significant.
Forward citations
Cited by 2 Pith papers
-
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.
-
New Insights on Unfolding and Fine-tuning Quantum Federated Learning
Deep unfolding with client-learned hyperparameters is claimed to improve quantum federated learning accuracy from roughly 55% to 90%, but the supporting proof and baseline data are not established.
Discussion (0). Sign in to comment.