Brief introduction to global optimization. Discussed the difficulty of the problem, and the inapplicability of the local approximations that dominate local optimization methods. The key in general with many global optimization is to find the right balance between global and local search. Essentially there are four categories of possible methods, depending on whether local and global searches are stochastic or deterministic. A genetic algorithm uses stochastic methods for both the global and local search; such algorithms can often be very flexible and easy to implement, but often also converge slowly. Multistart algorithms such as MLSL use stochastic global search combined with deterministic local search by standard local-optimization algorithms. A nice example of a completely deterministic algorithm is the DIRECT algorithm by Jones et al.

Described the DIRECT algorithm by Jones et al. Following the Jones paper, worked through a 1d example of optimization using the Lipshitz constant (an upper bound on the rate of change), and then relaxed this to identify the potentially optimal search regions by considering all possible Lipshitz constants. Showed that this reduces to a problem of finding the lower convex hull of a set of points (function values vs. diameter), and is technically a "dynamic convex hull" problem for which many efficient algorithms are known (although Jones et al. do not use this terminology). Trivial proof of convergence (for continuous objectives), although this is of limited utility because it does not tell us much about the convergence rate in practice.

Brief discussion of multistart algorithms, which do repeated local searches (using some local minimization algorithm) from different starting points, and discussed clustering heuristics to prevent repeated searches of the same local minima. In particular, discussed the multi-level single-linkage algorithm (MLSL) from A. H. G. Rinnooy Kan and G. T. Timmer, "Stochastic global optimization methods," Mathematical Programming, vol. 39, p. 27-78 (1987).