Distributed synchronous and asynchronous algorithms for semi-definite programming with diagonal constraints

TL;DR

This paper introduces distributed synchronous and asynchronous algorithms for large-scale semi-definite programming with diagonal constraints, reducing computational complexity and enabling application to image segmentation.

Contribution

It develops novel distributed algorithms based on low-rank and Burer-Monteiro factorization, improving efficiency and convergence in large-scale semi-definite programming.

Findings

Algorithms effectively escape saddle points and converge to optimal solutions.

Distributed methods outperform centralized algorithms in computational efficiency.

Application to image segmentation demonstrates practical effectiveness.

Abstract

This paper develops distributed synchronous and asynchronous algorithms for the large-scale semi-definite programming with diagonal constraints, which has wide applications in combination optimization, image processing and community detection. The information of the semi-definite programming is allocated to multiple interconnected agents such that each agent aims to find a solution by communicating to its neighbors. Based on low-rank property of solutions and the Burer-Monteiro factorization, we transform the original problem into a distributed optimization problem over unit spheres to reduce variable dimensions and ensure positive semi-definiteness without involving semi-definite projections, which are computationally expensive. For the distributed optimization problem, we propose distributed synchronous and asynchronous algorithms, both of which reduce computational burden and storage space compared with existing centralized algorithms. Specifically, the distributed synchronous algorithm almost surely escapes strict saddle points and converges to the set of optimal solutions to the optimization problem. In addition, the proposed distributed asynchronous algorithm allows communication delays and converges to the set of critical points to the optimization problem under mild conditions. By applying proposed algorithms to image segmentation applications, we illustrate the efficiency and convergence performance of the two proposed algorithms.