Survey on multi-objective-based parameter optimization for deep learning

Abstract

Deep learning models form some of the most powerful machine-learning models for the extraction of important features. Most of the designs of deep neural models (i.e., the initialization of parameters) are still manually tuned, hence, obtaining a model with high performance is exceedingly time-consuming and occasionally impossible. Optimizing the parameters of deep networks, therefore requires improved optimization algorithms with high convergence rates. The single objective-based optimization methods that are generally used are mostly time-consuming and do not guarantee optimum performance in all cases. Mathematical optimization problems that contain multiple objective functions that must be optimized simultaneously fall under the category of multi-objective optimization (sometimes referred to as Pareto optimization). Multi-objective optimization problems form one of the alternatives yet useful options for parameter optimization, however, this domain is a bit underexplored. In this survey, we focus on exploring the effectiveness of multi-objective optimization strategies for parameter optimization in conjunction with deep neural networks. The case studies that are used in this study focus on how the two methods are combined to provide valuable insights into the generation of predictions and analysis in multiple applications.