手法を比較

	Bayesian NSGA-II	多目的遺伝的アルゴリズム（MOGA）
分野	シミュレーション	シミュレーション
系統	Process / pipeline	Process / pipeline
提唱年	2002–2006	1984
提唱者	Emmerich, M. T. M. et al. (surrogate-assisted MO-EA); Deb et al. (NSGA-II base)	Schaffer, J. D. (early MOGA); Goldberg, D. E. (GA foundations)
種類	Surrogate-assisted multi-objective evolutionary algorithm	Population-based evolutionary optimizer
原典	Deb, K., Pratap, A., Agarwal, S., Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197.	Goldberg, D. E. (1989). Genetic algorithms in search, optimization, and machine learning. Addison-Wesley. ISBN: 9780201157673
別名	B-NSGA-II, Surrogate-Assisted NSGA-II, Gaussian Process NSGA-II, Bayesian Multi-Objective EA	MOGA, Multi-objective GA, Evolutionary multi-objective optimization, EMO
関連	3	4
概要	Bayesian NSGA-II integrates Gaussian process surrogate models (Bayesian metamodels) into the NSGA-II evolutionary loop to solve expensive multi-objective optimization problems. By replacing costly true function evaluations with fast probabilistic predictions, it discovers high-quality Pareto-front approximations with far fewer real evaluations than standard NSGA-II.	A Multi-Objective Genetic Algorithm (MOGA) is an evolutionary computation method that evolves a population of candidate solutions toward a Pareto-optimal front, simultaneously optimizing two or more conflicting objective functions. It avoids collapsing trade-offs into a single score, instead producing a set of non-dominated solutions for the decision-maker to choose among.