Learning Rate Optimization for Deep Neural Networks Using Lipschitz Bandits
This work addresses hyperparameter optimization for neural network training, offering incremental improvements in efficiency for machine learning practitioners.
The paper tackles the problem of tuning learning rates for deep neural networks by proposing a Lipschitz bandit-driven approach, which finds better learning rates using fewer evaluations and epochs compared to HyperOpt and BLiE, leading to more efficient training.
Learning rate is a crucial parameter in training of neural networks. A properly tuned learning rate leads to faster training and higher test accuracy. In this paper, we propose a Lipschitz bandit-driven approach for tuning the learning rate of neural networks. The proposed approach is compared with the popular HyperOpt technique used extensively for hyperparameter optimization and the recently developed bandit-based algorithm BLiE. The results for multiple neural network architectures indicate that our method finds a better learning rate using a) fewer evaluations and b) lesser number of epochs per evaluation, when compared to both HyperOpt and BLiE. Thus, the proposed approach enables more efficient training of neural networks, leading to lower training time and lesser computational cost.