Model Guided Sampling Optimization for Low-dimensional Problems
This work addresses optimization challenges for researchers and practitioners dealing with costly function evaluations, though it appears incremental as it builds upon existing Gaussian-process-based methods.
The paper tackles the problem of optimizing expensive black-box functions by introducing Model Guided Sampling Optimization (MGSO) as a more robust alternative to the EGO algorithm, showing it helps avoid local minima and achieves close-to-optimum solutions faster on low-dimensional or smooth problems.
Optimization of very expensive black-box functions requires utilization of maximum information gathered by the process of optimization. Model Guided Sampling Optimization (MGSO) forms a more robust alternative to Jones' Gaussian-process-based EGO algorithm. Instead of EGO's maximizing expected improvement, the MGSO uses sampling the probability of improvement which is shown to be helpful against trapping in local minima. Further, the MGSO can reach close-to-optimum solutions faster than standard optimization algorithms on low dimensional or smooth problems.