A0362
Title: New advances in algorithmic techniques for computing optimal designs
Authors: Irene Garcia Camacha Gutierrez - University of Castilla-La Mancha (Spain) [presenting]
Ricardo Negrete Gallego - University of Castilla-La Mancha (Spain)
Sergio Pozuelo Campos - University of Castilla-La Mancha (Spain)
Abstract: One of the biggest challenges in calculating optimal experimental designs is coping with the computational cost. Algorithmic techniques remain key in this field: While analytical solutions are often impractical, numerical techniques have become the most effective option. An innovative algorithm that combines the algorithms traditionally used in optimal experimental design with metaheuristic techniques is provided. For this purpose, the foundations of Wynn-Federov, multiplicative, and the particle Swarm optimization algorithms are suitably adapted. This combination not only enhances computational efficiency but also is more robust in facing complex optimization problems.
