Advancements in Multiobjective Hyperparameterization Optimization: A Comprehensive Review

This paper presents a comprehensive review of 25 scholarly papers published between 2018 and 2023, in an effort to summarize the most recent advances in multiobjective hyperparameterization optimization. Selection of hyperparameters for any machine learning model, and then statistically satisfying the many objectives, is a crucial task for the model’s performance. Since it involves the balancing of numerous contradictory objectives, the optimization of hyperparameters is an integral part of the fine-tuning process of machine learning models. The objective of this study is to examine trends and novel approaches in multiobjective hyperparameterization optimization by combining findings from a variety of sources. In this paper, we examine the evolution of algorithms used in the last five years to address this complex optimization problem, including a comprehensive examination of the methodology, performance indicators, and applications involved in these algorithms. The result of this paper is that it will be useful to researchers, and decision-makers because as it provides insights that can increase the efficiency of hyperparameter tuning.