Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking
Preprint
Abstract
This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by $n$ agents forming an undirected and connected graph. However, the efficiency of distributed optimization is often hindered by communication bottlenecks. To mitigate this, we propose the Quantized Riemannian Gradient Tracking (Q-RGT) algorithm, where agents update their local variables using quantized gradients. The introduction of quantization noise allows our algorithm to bypass the constraints of the accurate Riemannian projection operator (such as retraction), further improving iterative efficiency. To the best of our knowledge, this is the first algorithm to achieve an $\mathcal{O}(1/K)$ convergence rate in the presence of quantization, matching the convergence rate of methods without quantization. Additionally, we explicitly derive lower bounds on decentralized consensus associated with a function of quantization levels. Numerical experiments demonstrate that Q-RGT performs comparably to non-quantized methods while reducing communication bottlenecks and computational overhead.
Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Distributed Riemannian stochastic gradient tracking algorithm on the Stiefel manifoldAutomatica, 2025
- Decentralized projected Riemannian gradient method for smooth optimization on compact submanifolds embedded in the Euclidean spaceNumerische Mathematik, 2025
- Decentralized Riemannian Natural Gradient Methods with Kronecker Product ApproximationsJournal of the Operations Research Society of China, 2025
- Decentralized Proximal Gradient Algorithms With Linear Convergence RatesIEEE Transactions on Automatic Control, 2020
- Distributed Linearized Alternating Direction Method of Multipliers for Composite Convex Consensus OptimizationIEEE Transactions on Automatic Control, 2017
- A Riemannian conjugate gradient method for optimization on the Stiefel manifoldComputational Optimization and Applications, 2016
- Design and Analysis of Distributed Averaging With Quantized CommunicationIEEE Transactions on Automatic Control, 2016
- Distributed Subgradient Methods for Multi-Agent OptimizationIEEE Transactions on Automatic Control, 2009
- Equivariant adaptive source separationIEEE Transactions on Signal Processing, 1996
- Distributed asynchronous deterministic and stochastic gradient optimization algorithmsIEEE Transactions on Automatic Control, 1986