Derivation of Coordinate Descent Algorithms from Optimal Control Theory

Recently, it was posited that disparate optimization algorithms may be coalesced in terms of a central source emanating from optimal control theory. Here we further this proposition by showing how coordinate descent derived emerging new principle. In particular, show basic can using maximum principle and collection max functions as “control” Lyapunov functions. The convergence the resulting is thus connected to controlled dissipation their corresponding operational metric for search vector all cases given Hessian convex objective function.