Stochastic search using the natural gradient

Sun Yi, Daan Wierstra, Tom Schaul, Jürgen Schmidhuber

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

17 Scopus citations


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 tness, by eficiently calculating the inverse of the exact Fisher information matrix whereas previous methods had to use approximations. Other novel aspects of our method include optimal tness baselines and importance mixing, a procedure adjusting batches with minimal numbers of tness evaluations. The algorithm yields competitive results on a number of benchmarks. Copyright 2009.
Original languageEnglish (US)
Title of host publicationACM International Conference Proceeding Series
StatePublished - Sep 15 2009
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14


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

Cite this