Distributed Gradient Methods for Nonconvex Optimization: Local and Global Convergence Guarantees

The article discusses distributed gradient-descent algorithms for computing local and global minima in nonconvex optimization. For local optimization, we focus on distributed stochastic gradient descent (D-SGD)---a simple network-based variant of classical SGD. We discuss local minima convergence guarantees and explore the simple but critical role of the stable-manifold theorem in analyzing saddle-point avoidance. For global optimization, we discuss annealing-based methods in which slowly decaying noise is added to distributed gradient descent. Conditions are discussed under which convergence to global minima is guaranteed. Numerical examples illustrate the key concepts in the paper.