Derivative free models

[aimanian]

Our models are based on surrogate models to approximate the computationally expensive objective functions. Hence, derivative information, which is generally unavailable for black-box simulation ob- jective functions, is not available. I was wondering if your optimization algorithms can handle derivative free models.

[ajnebro]

Metaheuristics techniques, such as evolutionary algorithms, particle swarm optimization, etc. are derivative-free optimization algorithms (https://en.wikipedia.org/wiki/Derivative-free_optimization).

[aimanian]

Hello, Thanks for your reply. Is there any example, for a machine learning based model for model function? Can you please guide me how to solve a simple problem with, for example, a neural network based model function? Thank you, Anahita