Gaussian Adaptation with Decaying Matrix Adaptation Weights

초록

Gaussian Adaptation (GaA) is a black box op-timization algorithm that shares a similar evolution process with the well-studied Simulated Annealing (SA) and Covariance Matrix Adaptation Evolution Strategy (CMA-ES). To improve the convergence properties of GaA in optimization, this paper presents a variant of GaA that degenerates during its evolution process into algorithms with well-proven convergence properties. Specifically, the proposed GaA variant termed AwGaA employs an adaptive weighting of the covariance matrix update of the standard GaA. Consequently, as the evolution process progresses the algorithm degenerates into a variant of SA or (1+1)-CMA-ES. The performance of the proposed AwGaA is evaluated on 30 functions from the IEEE 2014 benchmark suite and compared favorably with the original GaA as well as 6 other leading algorithms. © 2023 IEEE.

키워드