Theoretical foundation for CMA-ES from information geometry perspective

DOI10.1007/s00453-011-9564-8zbMath1314.62091arXiv1206.0730OpenAlexW2034813183MaRDI QIDQ1945172

Isao Ono, Youhei Akimoto, Yuichi Nagata, Shigenobu Kobayashi

Publication date: 3 April 2013

Published in: Algorithmica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1206.0730

zbMATH Keywords

information geometrynatural gradient learningcontinuous optimizationCMA-ESexpectation-maximization algorithmsexpected fitness maximization

Mathematics Subject Classification ID

Directional data; spatial statistics (62H11) Parametric inference (62F99) Applications of mathematical programming (90C90) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

Global linear convergence of evolution strategies with recombination on scaling-invariant functions ⋮ Analysis of surrogate-assisted information-geometric optimization algorithms ⋮ CMA-ES-based structural topology optimization using a level set boundary expression -- application to optical and carpet cloaks

Uses Software

• CMA-ES

Cites Work

• Policy search for motor primitives in robotics
• Using Expectation-Maximization for Reinforcement Learning
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Theoretical foundation for CMA-ES from information geometry perspective