Deep Neural Network Hyperparameter Optimization with Orthogonal Array Tuning

TL;DR

This paper introduces an Orthogonal Array Tuning Method (OATM) for deep neural network hyper-parameter optimization, significantly reducing tuning time while maintaining performance across different network architectures.

Contribution

The paper presents a novel hyper-parameter tuning approach using orthogonal arrays, offering an efficient alternative to existing methods for deep learning models.

Findings

OATM reduces hyper-parameter tuning time significantly.

OATM achieves comparable or better performance than grid, random, and Bayesian methods.

The approach is validated on RNN and CNN architectures.

Abstract

Deep learning algorithms have achieved excellent performance lately in a wide range of fields (e.g., computer version). However, a severe challenge faced by deep learning is the high dependency on hyper-parameters. The algorithm results may fluctuate dramatically under the different configuration of hyper-parameters. Addressing the above issue, this paper presents an efficient Orthogonal Array Tuning Method (OATM) for deep learning hyper-parameter tuning. We describe the OATM approach in five detailed steps and elaborate on it using two widely used deep neural network structures (Recurrent Neural Networks and Convolutional Neural Networks). The proposed method is compared to the state-of-the-art hyper-parameter tuning methods including manually (e.g., grid search and random search) and automatically (e.g., Bayesian Optimization) ones. The experiment results state that OATM can significantly save the tuning time compared to the state-of-the-art methods while preserving the satisfying performance. The codes are open in GitHub (https://github.com/xiangzhang1015/OATM)