Automated Algorithm Selection on Continuous Black-Box Problems By Combining Exploratory Landscape Analysis and Machine Learning
Pascal Kerschke,Heike Trautmann +1 more
TL;DR: In this paper, an algorithm selection model for continuous black-box optimization problems is presented, based on the assumption that the function set of the Black-Box Optimization Benchmark is representative enough for practical applications.
read more
Abstract: In this paper, we build upon previous work on designing informative and efficient Exploratory Landscape Analysis features for characterizing problems' landscapes and show their effectiveness in automatically constructing algorithm selection models in continuous black-box optimization problems. Focussing on algorithm performance results of the COCO platform of several years, we construct a representative set of high-performing complementary solvers and present an algorithm selection model that - compared to the portfolio's single best solver - on average requires less than half of the resources for solving a given problem. Therefore, there is a huge gain in efficiency compared to classical ensemble methods combined with an increased insight into problem characteristics and algorithm properties by using informative features. Acting on the assumption that the function set of the Black-Box Optimization Benchmark is representative enough for practical applications the model allows for selecting the best suited optimization algorithm within the considered set for unseen problems prior to the optimization itself based on a small sample of function evaluations. Note that such a sample can even be reused for the initial population of an evolutionary (optimization) algorithm so that even the feature costs become negligible.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Benchmark for filter methods for feature selection in high-dimensional classification data
TL;DR: There is no group of filter methods that always outperforms all other methods, but recommendations onfilter methods that perform well on many of the data sets are made and groups of filters that are similar with respect to the order in which they rank the features are found.
625
Automated Algorithm Selection: Survey and Perspectives
TL;DR: This survey provides an overview of research in automated algorithm selection, ranging from early and seminal works to recent and promising application areas, and discusses algorithm selection in context with conceptually related approaches, such as algorithm configuration, scheduling, or portfolio selection.
463
•Posted Content
Benchmarking in Optimization: Best Practice and Open Issues
Thomas Bartz-Beielstein,Carola Doerr,Jakob Bossek,Sowmya Chandrasekaran,Tome Eftimov,Andreas Fischbach,Pascal Kerschke,Manuel López-Ibáñez,Katherine M. Malan,Jason H. Moore,Boris Naujoks,Patryk Orzechowski,Vanessa Volz,Markus Wagner,Thomas Weise +14 more
TL;DR: The article discusses eight essential topics in benchmarking: clearly stated goals, well-specified problems, suitable algorithms, adequate performance measures, thoughtful analysis, effective and efficient designs, comprehensible presentations, and guaranteed reproducibility.
121
Understanding the problem space in single-objective numerical optimization using exploratory landscape analysis
TL;DR: This article presents a method for visually determining the distribution of problems within a benchmark set using exploratory landscape analysis combined with clustering and t-sne visualization, and evaluates and explains the visualization this methodology produces.
83
Landscape-Aware Performance Prediction for Evolutionary Multiobjective Optimization
TL;DR: By providing effective tools for multiobjective landscape analysis, this work highlights that multiple features are required to capture problem difficulty, and provides further insights into the importance of ruggedness and multimodality to characterize multiobjectives combinatorial landscapes.
References
•Journal Article
R: A language and environment for statistical computing.
TL;DR: Copyright (©) 1999–2012 R Foundation for Statistical Computing; permission is granted to make and distribute verbatim copies of this manual provided the copyright notice and permission notice are preserved on all copies.
410.8K
Classification and Regression by randomForest
Andy Liaw,Matthew C. Wiener +1 more
- 01 Jan 2007
TL;DR: random forests are proposed, which add an additional layer of randomness to bagging and are robust against overfitting, and the randomForest package provides an R interface to the Fortran programs by Breiman and Cutler.
Domain-adversarial training of neural networks
Yaroslav Ganin,Evgeniya Ustinova,Hana Ajakan,Pascal Germain,Hugo Larochelle,François Laviolette,Mario Marchand,Victor Lempitsky +7 more
TL;DR: In this article, a new representation learning approach for domain adaptation is proposed, in which data at training and test time come from similar but different distributions, and features that cannot discriminate between the training (source) and test (target) domains are used to promote the emergence of features that are discriminative for the main learning task on the source domain.
Introduction to Evolutionary Computing
Agoston E. Eiben,James C. Smith +1 more
- 01 Jan 2015
TL;DR: In the second edition, the authors have reorganized the material to focus on problems, how to represent them, and then how to choose and design algorithms for different representations as discussed by the authors.
5.2K
Completely Derandomized Self-Adaptation in Evolution Strategies
TL;DR: This paper puts forward two useful methods for self-adaptation of the mutation distribution - the concepts of derandomization and cumulation and reveals local and global search properties of the evolution strategy with and without covariance matrix adaptation.