Technical Report: Partially Asynchronous Distributed Optimization on Riemannian Manifolds
math.OC
Submitted: 2026-11-04
Updated: 2026-11-08
Comments: 19 pages, 5 figures
Code: https://github.com/pooleya19/asynch-opt-on-manifolds-py
License: http://creativecommons.org/licenses/by/4.0/
The gist: There is a large body of work on distributed optimization for problems in Euclidean space.
Terminology
Abstract
There is a large body of work on distributed optimization for problems in Euclidean space. However, many existing algorithms and analyses do not directly transfer to problems defined on manifolds. Therefore, in this paper we propose a distributed asynchronous optimization algorithm for problems on Riemannian manifolds. The algorithm we develop is a parallelized form of Riemannian block coordinate descent in which all agents can compute and communicate asynchronously. We assume only "partial asynchrony", namely that all delays in computations and communications obey some finite bound, and we omit the common assumptions of convexity of the objective and compactness of the manifold. Under mild conditions, we prove that agents' iterates drive the Riemannian gradient of the objective to zero, and we derive a rate of convergence for the norm of the gradient. In simulations, we compare to a synchronous baseline algorithm under varying communication delays and numbers of agents. In example problems, we empirically show that our algorithm converges up to 8.5 times faster and attains up to 24 times lower suboptimality over a finite horizon.
Sources
- Distributed Pose Graph Optimization via Continuous Riemannian Dynamics
- A Brief Introduction to Manifold Optimization
- Distributed Riemannian Optimization in Geodesically Non-convex Environments
- Block Coordinate Descent on Smooth Manifolds: Convergence Theory and Twenty-One Examples
- Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise