Benchmarking separable natural evolution strategies on the noiseless and noisy black-box optimization testbeds

Natural Evolution Strategies (NES) are a recent member of the class of real-valued optimization algorithms that are based on adapting search distributions. Separable NES (SNES) are a variant of NES that scale linearly with problem dimension and are particularly appropriate for large, separable problems. This report provides the the most extensive empirical results on that algorithm to date, on both the noise-free and noisy BBOB testbeds.