Distributed gradient descent method with edge‐based event‐driven communication for non‐convex optimization
T. Adachi, Naoki Hayashi, Shigemasa Takai
Abstract
Abstract This paper considers an event‐driven distributed non‐convex optimization algorithm for a multi‐agent system, where each agent has a non‐convex cost function. The goal of the multi‐agent system is to minimize the global objective function, which is the sum of these local cost functions, in a distributed manner. To this end, each agent updates the own state by a consensus‐based gradient descent algorithm. The local information exchange among neighbor agents is carried out with an event‐triggered scheme to achieve consensus with less inter‐agent communication. Convergence to a critical point of the objective function and the validity of the proposed algorithm in numerical examples are shown.
Topics & Concepts
Gradient descentEnhanced Data Rates for GSM EvolutionControl theory (sociology)Computer scienceRegular polygonEvent (particle physics)Convex optimizationProximal Gradient MethodsMathematical optimizationMathematicsArtificial intelligenceControl (management)PhysicsGeometryArtificial neural networkQuantum mechanicsDistributed Control Multi-Agent SystemsStochastic Gradient Optimization TechniquesSparse and Compressive Sensing Techniques