SO-MI: A surrogate model algorithm for computationally expensive nonlinear mixed-integer black-box global optimization problems.
Juliane MüllerChristine A. ShoemakerRobert PichéPublished in: Comput. Oper. Res. (2013)
Keyphrases
- global optimization problems
- mixed integer
- computationally expensive
- black box
- objective function
- probabilistic model
- continuous variables
- computationally efficient
- cost function
- mathematical model
- dynamic programming
- optimal solution
- em algorithm
- optimization algorithm
- np hard
- learning algorithm
- convex hull
- parameter estimation
- multi objective
- differential evolution
- expectation maximization
- convergence rate
- computational complexity
- particle swarm optimization