Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification

TL;DR

This paper introduces a dynamic learning rate scheduler that adapts during training, significantly enhancing the efficiency and stability of neural networks in PINNs and image classification tasks.

Contribution

The paper proposes a novel dynamic learning rate scheduler that adjusts based on loss values, improving training speed and stability for complex neural network models.

Findings

DLRS accelerates training process

DLRS improves training stability

Enhanced performance in PINNs and image classification

Abstract

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.