We present a novel Natural Evolution Strategy (NES) variant, the Rank-One NES (R1-NES), which uses a low-rank approximation of the search distribution covariance matrix. The algorithm allows computation of the natural gradient with cost linear in the dimensionality of the parameter space, and excels in solving high-dimensional non-separable problems.
|Original language||English (US)|
|Title of host publication||GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion|
|Number of pages||2|
|State||Published - Aug 26 2013|