REVIEW 1 cited by
Distributed Riemannian Stochastic Gradient Tracking Algorithm on the Stiefel Manifold
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
Distributed Riemannian Stochastic Gradient Tracking Algorithm on the Stiefel Manifold
read the original abstract
This paper focus on investigating the distributed Riemannian stochastic optimization problem on the Stiefel manifold for multi-agent systems, where all the agents work collaboratively to optimize a function modeled by the average of their expectation-valued local costs. Each agent only processes its own local cost function and communicate with neighboring agents to achieve optimal results while ensuring consensus. Since the local Riemannian gradient in stochastic regimes cannot be directly calculated, we will estimate the gradient by the average of a variable number of sampled gradient, which however brings about noise to the system. We then propose a distributed Riemannian stochastic optimization algorithm on the Stiefel manifold by combining the variable sample size gradient approximation method with the gradient tracking dynamic. It is worth noticing that the suitably chosen increasing sample size plays an important role in improving the algorithm efficiency, as it reduces the noise variance. In an expectation-valued sense, the iterates of all agents are proved to converge to a stationary point (or neighborhood) with fixed step sizes. We further establish the convergence rate of the iterates for the cases when the sample size is exponentially increasing, polynomial increasing, or a constant, respectively. Finally, numerical experiments are implemented to demonstrate the theoretical results.
Forward citations
Cited by 1 Pith paper
-
Distributed Stochastic Proximal Algorithm on Riemannian Submanifolds for Weakly-convex Functions
A retraction-based distributed stochastic proximal framework reaches consensus and a nearly stationary point at rate O((1+κ_g)/√k) for weakly-convex costs on compact embedded submanifolds.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.