Seminar Details
2021-11-30 (14h) : A Generalized Worst-Case Complexity Analysis for Non-Monotone Line Searches
At Euler building (room a.002)
Organized by Mathematical Engineering
Speaker :
Nunes Grapiglia, Geovani
Abstract :
In this talk we discuss the worst-case complexity of a wide class of non-monotone line search methods for non-convex unconstrained minimization problems. For the algorithms in this class, the non monotonicity is controlled by a sequence of nonnegative parameters. We prove complexity bounds to achieve approximate first-order optimality even when this sequence is not summable. As a by-product, we obtain a unified global convergence result. Our generalized results allow more freedom for the development of new non-monotone line search algorithms. As an example, we design a non-monotone scheme related to the Metropolis rule. Preliminary numerical experiments suggest that the new method is suitable to nonconvex problems with many non-global local minimizers.