Varying Infimum Gradient Descent Algorithm for Agent–Server Systems With Uncertain Communication Network
Jing Chen, Min Gan, Quanmin Zhu, Yawen Mao
Abstract
This article studies agent-server system identification problems by using a varying infimum gradient descent (VI-GD) algorithm. To efficiently use the GD algorithm for the agent-server with noise, a VI-GD algorithm, which performs a preconditioning matrix before the negative direction of the GD algorithm, is developed. This algorithm can reduce the infimum of the convergence rates without full matrix inversion calculation and can be extended to the systems with ill-conditioned information matrix. Convergence analysis and the comparisons with other methods show the effectiveness of the proposed algorithm. Furthermore, the theoretical results are also verified through simulations.
Topics & Concepts
Infimum and supremumAlgorithmConvergence (economics)Gradient descentComputer scienceMatrix (chemical analysis)Mathematical optimizationMathematicsArtificial intelligenceDiscrete mathematicsArtificial neural networkComposite materialEconomicsEconomic growthMaterials scienceSparse and Compressive Sensing TechniquesDistributed Control Multi-Agent SystemsAdvanced Adaptive Filtering Techniques