Giter Club home page Giter Club logo

cec2021's Introduction

CEC 2021

About

This repository contains results of numerical experiments performed on CEC 2021 for the paper:

A new step-size adaptation rule for CMA-ES based on the population midpoint fitness

It also contains the source code of used optimization algorithms and scripts to reproduce conducted experiments.

Content

  • R/ stores implementation of used algorithms in R
  • data/ stores obtained data from numerical experiments:
    • cec13 has data from CEC 2013
    • cec17 has data from CEC 2017
    • cec21 has data from CEC 2021
  • time-complexity contains R script to compute complexity of considered algorithm in the paper
  • configs stores benchmark configuration files written in YAML.

Algorithms

Each algorithm is implemented in R programming language and based on the source code of the CRAN package {cmaesr}.

Data

Recorded data from experiments, i.e. error values (F(x) - F(x*)), is stored in m/ and M/ directories. The first directory contains the error values recorded with a budget step defined as in CEC 2021 specification:

d^(0:15/5 - 3) * maxFES

where d stands for the dimension and maxFES is budget for objective function evaluation.

The data from the directory M/ stores the error values recorded in the same manner as in CEC 2017 (or older):

c(0.01, 0.02, 0.03, 0.05, seq(0.1, 1, 0.1)) * maxFES

Benchmark configs

Experiments were performed using {cecb}, i.e. the R package written by me; mainly for the self-purposes. The package executes CECs experiments using the YAML data-serialization language. See the documentation for further details.

Also, we used {cecs} package which provides an interface from R to the benchmark functions implemented in C.

Experiments reproduction

If you want to reproduce our results you have to have installed docker in version 19.03.8 on your machine and run the commands written below in the root directory of the repository:

make build
make run cec=[CEC_VERSION | all]

These commands will build docker image and execute the bash script which takes options:

  • CEC_VERSION which takes values from {2013, 2017, 2021} to reproduce experiments only for the one CEC version
  • all which reproduces all experiments presented in the paper.

Contact

Feel free to contact me if you have any suggestions, questions, etc.: [email protected]

cec2021's People

Contributors

ewarchul avatar

Stargazers

 avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.