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 …

Selector: selecting a representative benchmark suite for reproducible statistical comparison

G Cenikj, RD Lang, AP Engelbrecht, C Doerr… - Proceedings of The …, 2022 - dl.acm.org
Fair algorithm evaluation is conditioned on the existence of high-quality benchmark datasets
that are non-redundant and are representative of typical optimization scenarios. In this …

Towards feature-based performance regression using trajectory data

A Jankovic, T Eftimov, C Doerr - … , EvoApplications 2021, Held as Part of …, 2021 - Springer
Black-box optimization is a very active area of research, with many new algorithms being
developed every year. This variety is needed, on the one hand, since different algorithms …

Transfer learning analysis of multi-class classification for landscape-aware algorithm selection

U Škvorc, T Eftimov, P Korošec - mathematics, 2022 - mdpi.com
In optimization, algorithm selection, which is the selection of the most suitable algorithm for a
specific problem, is of great importance, as algorithm performance is heavily dependent on …

Deep-ELA: Deep Exploratory Landscape Analysis with Self-Supervised Pretrained Transformers for Single-and Multi-Objective Continuous Optimization Problems

MV Seiler, P Kerschke, H Trautmann - arxiv preprint arxiv:2401.01192, 2024 - arxiv.org
In many recent works, the potential of Exploratory Landscape Analysis (ELA) features to
numerically characterize, in particular, single-objective continuous optimization problems …

Explainable landscape analysis in automated algorithm performance prediction

R Trajanov, S Dimeski, M Popovski, P Korošec… - … Conference on the …, 2022 - Springer
Predicting the performance of an optimization algorithm on a new problem instance is
crucial in order to select the most appropriate algorithm for solving that problem instance …

Using structural bias to analyse the behaviour of modular CMA-ES

D Vermetten, F Caraffini, B van Stein… - Proceedings of the …, 2022 - dl.acm.org
The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a commonly used
iterative optimisation heuristic for optimising black-box functions. CMA-ES comes in many …

[HTML][HTML] Opt2Vec-a continuous optimization problem representation based on the algorithm's behavior: A case study on problem classification

P Korošec, T Eftimov - Information Sciences, 2024 - Elsevier
Abstract Characterization of the optimization problem is a crucial task in many recent
optimization research topics (eg, explainable algorithm performance assessment, and …

A Survey of Meta-features Used for Automated Selection of Algorithms for Black-box Single-objective Continuous Optimization

G Cenikj, A Nikolikj, G Petelin, N van Stein… - arxiv preprint arxiv …, 2024 - arxiv.org
The selection of the most appropriate algorithm to solve a given problem instance, known as
algorithm selection, is driven by the potential to capitalize on the complementary …

Generalization Ability of Feature-based Performance Prediction Models: A Statistical Analysis across Benchmarks

A Nikolikj, A Kostovska, G Cenikj, C Doerr… - arxiv preprint arxiv …, 2024 - arxiv.org
This study examines the generalization ability of algorithm performance prediction models
across various benchmark suites. Comparing the statistical similarity between the problem …