Title: Hyperparameter tuning of deep learning models using MaxPro space filling methodology

Authors: Shilpa Gupta; Harsh Raj Jeripothula; Douglas C. Montgomery

Addresses: San Jose State University, One Washington Square, San Jose, CA 95192-0085, USA ' San Jose State University, One Washington Square, San Jose, CA 95192-0085, USA ' Arizona State University, Mail Code: 8809, Tempe, AZ 85287, USA

Abstract: Hyperparameter tuning is crucial for optimising deep learning models. Traditional methods like grid search and random search can be time consuming and computationally expensive. This study explores space filling methodology for hyperparameter tuning, aiming to explore the hyperparameter space for optimal configurations. Hyperparameters are tuned for ResNet models using CIFAR-10 dataset and compared MaxPro space filling methodology with randomised search and grid search in terms of accuracy and computational costs. A greater accuracy was observed for the hyperparameters selected based on space filling methodology as compared to the randomised search while the runtime is similar for both. By systematically exploring the hyperparameter space, space filling offers an efficient approach to hyperparameter tuning, enabling faster model development. The findings underscore space filling methodology's potential for effective hyperparameter tuning, especially in resource constrained scenarios.

Keywords: experimental design; space filling design; MaxPro design; hyperparameter tuning; computer vision; computer experiments.

DOI: 10.1504/IJEDPO.2025.152135

International Journal of Experimental Design and Process Optimisation, 2025 Vol.8 No.1/2, pp.52 - 61

Received: 26 Feb 2025
Accepted: 15 Oct 2025
Published online: 09 Mar 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article