
PMBO introduces a novel approach by combining polynomial approximation with Bayesian optimization, outperforming classic methods and showing robustness in low-dimensional optimization problems.


coremsg

enhancing-black-box-optimization-with-polynomial-surrogates-pmbo-study


Enhancing Black-Box Optimization with Polynomial Surrogates: PMBO Study


title_rewrite


PMBO combines polynomial approximation with Bayesian optimization to outperform classic methods and provide robustness in low-dimensional optimization problems.


pmbo-enhancing-black-box-optimization-through-multivariate-polynomial-surrogates


PMBO: Enhancing Black-Box Optimization Through Multivariate Polynomial Surrogates



This paper introduces PWAS, a novel surrogate-based global optimization algorithm that efficiently solves linearly constrained mixed-variable problems by constructing piecewise affine surrogates of expensive-to-evaluate objective functions, and explores its application in preference-based optimization with a variant called PWASp.


global-and-preference-based-optimization-for-mixed-variable-problems-using-piecewise-affine-surrogates


Global and Preference-based Optimization for Mixed-Variable Problems Using Piecewise Affine Surrogates
