On the convergence result of the gradient-push algorithm on directed graphs with constant stepsize
Gradient-push algorithm has been widely used for decentralized optimization problems when the connectivity network is a direct graph. This paper shows that the gradient-push algorithm with stepsize α>0 converges exponentially fast to an O(α)-neighborhood of the optimizer under the assumption that each cost is smooth and the total cost is strongly convex. Numerical experiments are provided to support the theoretical convergence results.
READ FULL TEXT