VRBBON — line search in noisy unconstrained black box optimization

In this paper, a new randomized solver for noisy unconstrained black box optimization, called VRBBON, is discussed. Complexity bounds in the presence of noise for nonconvex, convex, and strongly convex functions are studied. Two effective ingredients of VRBBON are an improved derivative-free line search algorithm with many heuristic enhancements and quadratic models in adaptively determined … Read more