Related references
Note: Only part of the references are listed.
Article
Computer Science, Theory & Methods
Kate Smith-Miles et al.
Summary: Instance Space Analysis (ISA) is a methodology developed to support objective testing of algorithms and assess the diversity of test instances. It enables visualization of the entire space of possible test instances and provides insights into how algorithm performance is affected by instance properties. This article serves as a comprehensive tutorial on the ISA methodology, including details of algorithms and software tools. A case study on university timetabling is presented to illustrate the methodology and tools.
ACM COMPUTING SURVEYS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Ana Nikolikj et al.
Summary: The study proposes a methodology based on problem landscape features and explainable machine learning models for automated algorithm performance prediction. The results show that performance prediction of different DE configurations relies on different landscape features, but similar feature portfolios are important for DE configurations with similar performance.
BIOINSPIRED OPTIMIZATION METHODS AND THEIR APPLICATIONS
(2022)
Proceedings Paper
Computer Science, Cybernetics
Marcelo de Souza et al.
Summary: This study proposes an offline algorithm configuration method that sets parameter values automatically based on instance size using non-constant models. The method shows significant performance gains compared to traditional instance-independent configuration methods.
PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'22)
(2022)
Article
Computer Science, Software Engineering
Nikolaus Hansen et al.
Summary: COCO is an open-source platform for Comparing Continuous Optimizers in a black-box setting, aiming to automate the benchmarking of numerical optimization algorithms. It allows benchmarking deterministic and stochastic solvers for both single and multiobjective optimization in the same framework.
OPTIMIZATION METHODS & SOFTWARE
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Risto Trajanov et al.
Summary: The study investigates explainable landscape-aware regression models which estimate the contribution of each landscape feature to the prediction of the optimization algorithm performance on a global and local level. Experimental results show that different problem instances require different sets of features, indicating the need for further personalization of the landscape space when training an automated algorithm performance prediction model.
2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Ryan Dieter Lang et al.
Summary: This study introduces a method to determine the minimum sample size required for robust exploratory landscape analysis measures, and utilizes self-organizing feature map to cluster a comprehensive set of benchmark functions, proposing a benchmark suite with improved coverage in single-objective, boundary-constrained problem spaces.
Article
Computer Science, Information Systems
Tome Eftimov et al.
INFORMATION SCIENCES
(2017)
Article
Statistics & Probability
Gerard Biau et al.
Article
Statistics & Probability
Gerard Biau et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Pascal Kerschke et al.
GECCO'15: PROCEEDINGS OF THE 2015 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE
(2015)
Article
Computer Science, Artificial Intelligence
Joaquin Derrac et al.
SWARM AND EVOLUTIONARY COMPUTATION
(2011)
