Multi-objective Optimization Evolutionary Algorithms Applied to Paroxysmal Atrial Fibrillation Diagnosis Based on the k-Nearest Neighbours Classifier

A survey on multi-objective hyperparameter optimization algorithms for machine learning

“…Fig. 3 Example of the interplay between the HPO algorithm and the target ML algorithm (in this case, an ANN for predicting house prices) these trade-offs is often crucial: e.g., in medical diagnostics (de Toro et al 2002), the simultaneous consideration of objectives such as sensitivity and specificity is essential to determine if the machine learning model can be used in practice. The goal in multiobjective HPO is to obtain the Pareto-optimal solutions, i.e., those solutions for which none of the objectives can be improved without negatively affecting any other objective.…”

A survey on multi-objective hyperparameter optimization algorithms for Machine Learning

“…Usually, there is a trade-off among the different objectives: for instance, between the performance of a model and training time (increasing the accuracy of a model often requires larger amounts of data and, hence, a higher training time; see e.g., Rajagopal et al (2020)), or between different error-based measures (e.g., between confusion matrix-based measures (Tharwat, 2020) of a binary classification problem; see Horn and Bischl (2016)). Considering these trade-offs is often crucial: e.g., in medical diagnostics (de Toro, Ros, Mota, & Ortega, 2002), the simultaneous consideration of objectives such as sensitivity and specificity is essential to determine if the machine learning model can be used in practice. The goal in multi-objective HPO is to obtain the Paretooptimal solutions, i.e., those solutions for which none of the objectives can be improved without negatively affecting any other objective.…”