Enhancing Multi-Objective Machine Learning with an Optimized Lexicographic Approach: Determining the Tolerance Threshold
Resumo
Determining optimal tolerance in lexicographic multi-objective optimization is crucial for robust results. This paper introduces a machine learning algorithm that automatically sets the appropriate tolerance, optimizing the lexicographic strategy and enhancing the analysis of tolerance impact on outcomes. Applied to various datasets, our method consistently provides insights into the relationship between tolerance and model performance. Results show that automatic tolerance optimization improves computational efficiency and accuracy. These findings highlight the importance of addressing tolerance in multi-objective optimization.
Palavras-chave:
Machine Learning, Lexicographic, Tolerance
Referências
Ahlert, M. and Kliemt, H. (2001). A lexicographic decision rule with tolerances. Analyse Kritik, 23.
Andrade, F. (2020). Metodologia multicritério de apoio à decisão - a gestão da informação no processo decisório.
Basgalupp, M., Barros, R., de Carvalho, A., and Freitas, A. (2014). Evolving decision trees with beam search-based initialization and lexicographic multi-objective evaluation. Information Sciences, 258.
Basgalupp, M., Barros, R., de Carvalho, A., Freitas, A., and Ruiz, D. (2009). Legal-tree: A lexicographic multi-objective genetic algorithm for decision tree induction. pages 1085–1090.
Biswas, A., Fuentes, C., and Hoyle, C. (2021). A mo-bayesian optimization approach using the weighted tchebycheff method. Journal of Mechanical Design, 144.
Boriwan, P., Ehrgott, M., Kuroiwa, D., and Petrot, N. (2020). The lexicographic tolerable robustness concept for uncertain multi-objective optimization problems: A study on water resources management. Sustainability, 12.
Boriwan, P., Kuroiwa, D., and Petrot, N. (2021). On the properties of lexicographic tolerable robust solution sets for uncertain multi-objective optimization problems. Carpathian Journal of Mathematics, 37:25–34.
Andrade, F. (2020). Metodologia multicritério de apoio à decisão - a gestão da informação no processo decisório.
Basgalupp, M., Barros, R., de Carvalho, A., and Freitas, A. (2014). Evolving decision trees with beam search-based initialization and lexicographic multi-objective evaluation. Information Sciences, 258.
Basgalupp, M., Barros, R., de Carvalho, A., Freitas, A., and Ruiz, D. (2009). Legal-tree: A lexicographic multi-objective genetic algorithm for decision tree induction. pages 1085–1090.
Biswas, A., Fuentes, C., and Hoyle, C. (2021). A mo-bayesian optimization approach using the weighted tchebycheff method. Journal of Mechanical Design, 144.
Boriwan, P., Ehrgott, M., Kuroiwa, D., and Petrot, N. (2020). The lexicographic tolerable robustness concept for uncertain multi-objective optimization problems: A study on water resources management. Sustainability, 12.
Boriwan, P., Kuroiwa, D., and Petrot, N. (2021). On the properties of lexicographic tolerable robust solution sets for uncertain multi-objective optimization problems. Carpathian Journal of Mathematics, 37:25–34.
Publicado
17/11/2024
Como Citar
FERNANDES, Guilherme G. D.; MEDEIROS, Talles H..
Enhancing Multi-Objective Machine Learning with an Optimized Lexicographic Approach: Determining the Tolerance Threshold. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 21. , 2024, Belém/PA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 906-917.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2024.245204.