An asynchronous implementation of the limited memory CMA-ES: First results

Viktor Arkhipov, Maxim Buzdalov

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

Abstract

We present our first results on the problem of asynchronous implementation of the LM-CMA-ES algorithm, which is a modern evolution strategy for solving complex large-scale continuous optimization problems. Our implementation converges with the linear speed on the Sphere benchmark problem, and CPU utilization is almost perfect when the computational cost of the fitness function is relatively high.

Original languageEnglish
Title of host publication21st International Conference on Soft Computing
Subtitle of host publicationEvolutionary Computation, Genetic Programming, Swarm Intelligence, Fuzzy Logic, Neural Networks, Chaos, Bayesian Methods, Intelligent Image Processing, Bio-Inspired Robotics, MENDEL 2015
Pages43-46
Number of pages4
Volume2015-January
Publication statusPublished - 2015
Externally publishedYes
Event21st International Conference on Soft Computing: Evolutionary Computation, Genetic Programming, Swarm Intelligence, Fuzzy Logic, Neural Networks, Chaos, Bayesian Methods, Intelligent Image Processing, Bio-Inspired Robotics, MENDEL 2015 - Brno, Czech Republic
Duration: 23 Jun 201525 Jun 2015

Publication series

NameMendel
ISSN (Print)1803-3814

Conference

Conference21st International Conference on Soft Computing: Evolutionary Computation, Genetic Programming, Swarm Intelligence, Fuzzy Logic, Neural Networks, Chaos, Bayesian Methods, Intelligent Image Processing, Bio-Inspired Robotics, MENDEL 2015
Country/TerritoryCzech Republic
CityBrno
Period23 Jun 201525 Jun 2015

Keywords

  • Asynchronous algorithms
  • CMA-ES

Fingerprint

Dive into the research topics of 'An asynchronous implementation of the limited memory CMA-ES: First results'. Together they form a unique fingerprint.

Cite this