This short note considers and resolves the apparent contradiction between known worst-case complexity results for first and second-order methods for solving unconstrained smooth nonconvex optimization problems and a recent note by Jarre (2011) implying a very large lower bound on the number of iterations required to reach the solution’s neighbourhood for a specific problem with variable dimension.
Citation
Technical Report naXys-20-2011, Namur Center for Complex Systems, University of Namur, Belgium