Use este identificador para citar ou linkar para este item: http://repositorio.ufla.br/jspui/handle/1/40789
Título: Optimal decision trees for the algorithm selection problem: integer programming based approaches
Palavras-chave: Algorithm selection problem
Feature-based parameter tuning
Decision trees
Data mining
Integer programming
Variable neighborhood search
COIN-OR branch and cut
Algoritmo de seleção
Árvores de decisão
Problema de Programação Inteira
Mineração de dados
Data do documento: Set-2019
Editor: International Federation of Operational Research Societies (IFORS)
Citação: VILAS BOAS, M. G. et al. Optimal decision trees for the algorithm selection problem: integer programming based approaches. International Transactions in Operational Research, [S.I.], Sept. 2019. DOI: 10.1111/itor.12724
Resumo: Even though it is well known that for most relevant computational problems, different algorithms may perform better on different classes of problem instances, most researchers still focus on determining a single best algorithmic configuration based on aggregate results such as the average. In this paper, we propose integer programming‐based approaches to build decision trees for the algorithm selection problem. These techniques allow the automation of three crucial decisions: (urn:x-wiley:09696016:media:itor12724:itor12724-math-0001) discerning the most important problem features to determine problem classes, (urn:x-wiley:09696016:media:itor12724:itor12724-math-0002) grouping the problems into classes, and (urn:x-wiley:09696016:media:itor12724:itor12724-math-0003) selecting the best algorithm configuration for each class. To evaluate this new approach, extensive computational experiments were executed using the linear programming algorithms implemented in the COIN‐OR branch‐and‐cut solver across a comprehensive set of instances, including all MIPLIB benchmark instances. The results exceeded our expectations. While selecting the single best parameter setting across all instances decreased the total running time by 22%, our approach decreased the total running time by 40% on average across 10‐fold cross‐validation experiments. These results indicate that our method generalizes quite well and does not overfit.
URI: https://onlinelibrary.wiley.com/doi/10.1111/itor.12724
http://repositorio.ufla.br/jspui/handle/1/40789
Aparece nas coleções:DCC - Artigos publicados em periódicos

Arquivos associados a este item:
Não existem arquivos associados a este item.


Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.

Ferramentas do administrador