Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
This addresses the problem of inefficient training due to static learning rates for researchers and practitioners in machine learning, but it is incremental as it builds on existing scheduling methods.
The paper tackles the challenge of training neural networks by introducing a dynamic learning rate scheduler (DLRS) that adapts based on loss values, showing it accelerates training and improves stability in experiments on PINNs and image classification.
Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made. The learning rate is one of such crucial hyperparameters, which is usually kept static during the training process. Learning dynamics in complex systems often requires a more adaptive approach to the learning rate. This adaptability becomes crucial to effectively navigate varying gradients and optimize the learning process during the training process. In this paper, a dynamic learning rate scheduler (DLRS) algorithm is presented that adapts the learning rate based on the loss values calculated during the training process. Experiments are conducted on problems related to physics-informed neural networks (PINNs) and image classification using multilayer perceptrons and convolutional neural networks, respectively. The results demonstrate that the proposed DLRS accelerates training and improves stability.