A Linearly Convergent Doubly Stochastic Gauss-Seidel Algorithm for Solving Linear Equations and A Certain Class of Over-Parameterized Optimization Problems

Meisam Razaviyayn, Mingyi Hong, Navid Reyhanian +1

Consider the classical problem of solving a general linear system of equations $Ax=b$. It is well known that the (successively over relaxed) Gauss-Seidel scheme and many of its var…