We consider a class of nonsmooth optimization problems over the Stiefel manifold, in which objective function is weakly convex ambient Euclidean space. Such are ubiquitous engineering applications but still largely unexplored. present family Riemannian subgradient-type methods---namely subgradient, incremental and stochastic subgradient methods---to solve these show that they all have an iterat...

In this article, a stochastic incremental subgradient algorithm for the minimization of sum convex functions is introduced. The method sequentially uses partial information, and sequence subgradients determined by general Markov chain. This makes it suitable to be used in networks, where path information flow stochastically selected. We prove convergence weighted objective function, weights are...