The title of his talks is: „Surrogate Model-Based Multi-Objective Optimization Using
Desirability Functions“
Abstract: The desirability function approach is an established and widely adopted method in industry for optimizing multiple response processes. It is seldomly used in multi-criteria hyperparameter tuning.
This article fills this gap. It provides an introduction to the desirability function approach to multi-objective optimization (direct and surrogate model-based), and multi-objective hyperparameter
tuning. This work is based on the paper by Kuhn. It presents a Python implementation of Kuhn’s R package desirability. After the desirability-function approach is introduced, two examples
are given that demonstrate how to use desirability functions for classical optimization via response surface modeling and hyperparameter tuning of a neural network, which is implemented in
PyTorch.
The article discusses the following research questions:
(a) How can the desirability function approach be used for multi-
objective optimization and hyperparameter tuning?
(b) What are advantages and disadvantages of the desirability function approach
compared to other multi-objective optimization methods?
(c) How can the desirability function approach be improved?
More about the SAEOpt Workshop @GECCO2025: Surrogate-Assisted Evolutionary Optimisation Workshop