SwiftCMA
Released 2019
Download on GitHub

SwiftCMA is a pure-Swift implementation of Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES).
Santiago Gonzalez Ph.D. Student slgonzalez [at] utexas edu
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization 2020
Santiago Gonzalez and Risto Miikkulainen, In Proceedings of the 2020 IEEE Congress on Evolutionary Computation (CEC), July 2020.
Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization 2020
Santiago Gonzalez and Risto Miikkulainen, To Appear arXiv:2002.00059 (2020).