On the statistical learning ability of evolution strategies

DOI10.1145/3040718.3040722MaRDI QIDQ5738865zbMATH OpenOpenAlexFDO

Authors Ofer M. Shir, Amir Yehudayoff

Publication date 13 June 2017

Published in Proceedings of the 14th ACM/SIGEVO Conference on Foundations of Genetic Algorithms (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1145/3040718.3040722

zbMATH Keywords

covarianceevolution strategiesHessianlimit distributionorder statisticsstatistical landscape learning

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Order statistics; empirical distribution functions (62G30) Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Recommendations

• On the covariance-Hessian relation in evolution strategies
• Globally convergent evolution strategies
• Theoretical foundation for CMA-ES from information geometry perspective
• scientific article; zbMATH DE number 1664952
• Efficient covariance matrix update for variable metric evolution strategies

Cited in

(5)

• Efficient covariance matrix update for variable metric evolution strategies
• Theoretical foundation for CMA-ES from information geometry perspective
• On the covariance-Hessian relation in evolution strategies
• A more efficient rank-one covariance matrix update for evolution strategies
• Evolutionary Algorithms with Competing Heuristics in Computational Statistics

This page was built for publication: On the statistical learning ability of evolution strategies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5738865)