A Stochastic Second-Order Proximal Method for Distributed Optimization

We propose a distributed stochastic second-order proximal (St-SoPro) method that enables agents in network to cooperatively minimize the sum of their local loss functions without any centralized coordination. St-SoPro incorporates decentralized approximation into an augmented Lagrangian function, and randomly samples gradients Hessian matrices update, so it is efficient solving large-scale problems. show for restricted strongly convex smooth problems, linearly converge expectation neighborhood optimum, can be arbitrarily small under proper parameter settings. Simulations over real machine learning datasets demonstrate outperforms several state-of-the-art methods terms convergence speed as well computation communication costs.