Stochastic search using the natural gradient

Sun Yi, Daan Wierstra, Tom Schaul, Jürgen Schmidhuber

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

48 Scopus citations

Abstract

To optimize unknown 'fitness' functions, we present Natural Evolution Strategies, a novel algorithm that constitutes a principled alternative to standard stochastic search methods. It maintains a multinormal distribution on the set of solution candidates. The Natural Gradient is used to update the distribution's parameters in the direction of higher expected fitness, by efficiently calculating the inverse of the exact Fisher information matrix whereas previous methods had to use approximations. Other novel aspects of our method include optimal fitness baselines and importance mixing, a procedure adjusting batches with minimal numbers of fitness evaluations. The algorithm yields competitive results on a number of benchmarks.
Original languageEnglish (US)
Title of host publicationProceedings of the 26th International Conference On Machine Learning, ICML 2009
Pages1161-1168
Number of pages8
StatePublished - Dec 9 2009
Externally publishedYes

Fingerprint

Dive into the research topics of 'Stochastic search using the natural gradient'. Together they form a unique fingerprint.

Cite this