Investigating the impact of adaptation sampling in natural evolution strategies on black-box optimization testbeds
Tom Schaul · 2012
Natural Evolution Strategies (NES) are a recent member of the class of real-valued optimization algorithms that are based on adapting search distributions. Exponential NES (xNES) are the most common instantiation of NES, and particularly appropriate for the BBOB 2012 benchmarks, given that many are non-separable, and their relatively small problem dimensions. The technique of adaptation sampling, which adapts learning rates online further improves the algorithm's performance. This report provides an extensive empirical comparison to study the impact of adaptation sampling in xNES, both on the noise-free and noisy BBOB testbeds.