A linear time natural evolution strategy for non-separable functions

Yi Sun, Tom Schaul, Faustino Gomez, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Scopus citations

Abstract

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 languageEnglish (US)
Title of host publicationGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion
Pages61-62
Number of pages2
DOIs
StatePublished - Aug 26 2013
Externally publishedYes

Fingerprint

Dive into the research topics of 'A linear time natural evolution strategy for non-separable functions'. Together they form a unique fingerprint.

Cite this