Automated algorithm selection on continuous black-box problems by combining exploratory landscape analysis and machine learning

P Kerschke, H Trautmann - Evolutionary computation, 2019‏ - direct.mit.edu
In this article, we build upon previous work on designing informative and efficient
Exploratory Landscape Analysis features for characterizing problems' landscapes and show …

Evolutionary algorithms for parameter optimization—thirty years later

THW Bäck, AV Kononova, B van Stein… - Evolutionary …, 2023‏ - ieeexplore.ieee.org
Thirty years, 1993–2023, is a huge time frame in science. We address some major
developments in the field of evolutionary algorithms, with applications in parameter …

Llamea: A large language model evolutionary algorithm for automatically generating metaheuristics

N van Stein, T Bäck - IEEE Transactions on Evolutionary …, 2024‏ - ieeexplore.ieee.org
Large Language Models (LLMs) such as GPT-4 have demonstrated their ability to
understand natural language and generate complex code snippets. This paper introduces a …

Per-run algorithm selection with warm-starting using trajectory-based features

A Kostovska, A Jankovic, D Vermetten… - … Conference on Parallel …, 2022‏ - Springer
Per-instance algorithm selection seeks to recommend, for a given problem instance and a
given performance criterion, one or several suitable algorithms that are expected to perform …

Benchmarking discrete optimization heuristics with IOHprofiler

C Doerr, F Ye, N Horesh, H Wang, OM Shir… - Proceedings of the …, 2019‏ - dl.acm.org
Automated benchmarking environments aim to support researchers in understanding how
different algorithms perform on different types of optimization problems. Such comparisons …

IOHanalyzer: Detailed performance analyses for iterative optimization heuristics

H Wang, D Vermetten, F Ye, C Doerr… - ACM Transactions on …, 2022‏ - dl.acm.org
Benchmarking and performance analysis play an important role in understanding the
behaviour of iterative optimization heuristics (IOHs) such as local search algorithms, genetic …

Tuning as a means of assessing the benefits of new ideas in interplay with existing algorithmic modules

J de Nobel, D Vermetten, H Wang, C Doerr… - Proceedings of the …, 2021‏ - dl.acm.org
Introducing new algorithmic ideas is a key part of the continuous improvement of existing
optimization algorithms. However, when introducing a new component into an existing …

Modular differential evolution

D Vermetten, F Caraffini, AV Kononova… - Proceedings of the …, 2023‏ - dl.acm.org
New contributions in the field of iterative optimisation heuristics are often made in an
iterative manner. Novel algorithmic ideas are not proposed in isolation, but usually as …

Landscape-aware fixed-budget performance regression and algorithm selection for modular CMA-ES variants

A Jankovic, C Doerr - Proceedings of the 2020 Genetic and Evolutionary …, 2020‏ - dl.acm.org
Automated algorithm selection promises to support the user in the decisive task of selecting
a most suitable algorithm for a given problem. A common component of these machine …

Learning step-size adaptation in CMA-ES

G Shala, A Biedenkapp, N Awad, S Adriaensen… - Parallel Problem Solving …, 2020‏ - Springer
An algorithm's parameter setting often affects its ability to solve a given problem, eg,
population-size, mutation-rate or crossover-rate of an evolutionary algorithm. Furthermore …