Exponential natural evolution strategies

Abstract

The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness. Like the well-known CMA-ES, the most competitive algorithm in the field, NES comes with important invariance properties. In this paper, we introduce a number of elegant and efficient improvements of the basic NES algorithm. First, we propose to parameterize the positive definite covariance matrix using the exponential map, which allows the covariance matrix to be updated in a vector space. This new technique makes the algorithm completely invariant under linear transformations of the underlying search space, which was previously achieved only in the limit of small step sizes. Second, we compute all updates in the <i>natural</i> coordinate system, such that the natural gradient coincides with the vanilla gradient. This way we avoid the computation of the inverse Fisher information matrix, which is the main computational bottleneck of the original NES algorithm. Our new algorithm, exponential NES (xNES), is significantly simpler than its predecessors. We show that the various update rules in CMA-ES are closely related to the natural gradient updates of xNES. However, xNES is more principled than CMA-ES, as all the update rules needed for covariance matrix adaptation are derived from a single principle. We empirically assess the performance of the new algorithm on standard benchmark functions

DOI: 10.1145/1830483.1830557

Extracted Key Phrases

3 Figures and Tables

01020302008200920102011201220132014201520162017
Citations per Year

100 Citations

Semantic Scholar estimates that this publication has 100 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Glasmachers2010ExponentialNE, title={Exponential natural evolution strategies}, author={Tobias Glasmachers and Tom Schaul and Yi Sun and Daan Wierstra and J{\"{u}rgen Schmidhuber}, booktitle={GECCO}, year={2010} }