Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning

TL;DR

This paper introduces MORL, a novel multi-fidelity optimization method that incorporates CNN training dynamics to improve hyperparameter tuning efficiency and accuracy, outperforming existing methods like SHA and Hyperband.

Contribution

MORL integrates CNN optimization processes into multi-fidelity hyperparameter tuning, addressing slow-start issues and enhancing low-fidelity approximation accuracy.

Findings

MORL outperforms SHA and Hyperband in various image classification tasks.

MORL achieves significant hyperparameter tuning improvements within practical budgets.

Experiments demonstrate MORL's effectiveness across transfer and semi-supervised learning.

Abstract

Despite the evolution of Convolutional Neural Networks (CNNs), their performance is surprisingly dependent on the choice of hyperparameters. However, it remains challenging to efficiently explore large hyperparameter search space due to the long training times of modern CNNs. Multi-fidelity optimization enables the exploration of more hyperparameter configurations given budget by early termination of unpromising configurations. However, it often results in selecting a sub-optimal configuration as training with the high-performing configuration typically converges slowly in an early phase. In this paper, we propose Multi-fidelity Optimization with a Recurring Learning rate (MORL) which incorporates CNNs' optimization process into multi-fidelity optimization. MORL alleviates the problem of slow-starter and achieves a more precise low-fidelity approximation. Our comprehensive experiments on general image classification, transfer learning, and semi-supervised learning demonstrate the effectiveness of MORL over other multi-fidelity optimization methods such as Successive Halving Algorithm (SHA) and Hyperband. Furthermore, it achieves significant performance improvements over hand-tuned hyperparameter configuration within a practical budget.