Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks
This work addresses the challenge for practitioners in efficiently training deep learning models by providing tools to monitor and control hyperparameters, though it is incremental as it builds on existing training optimization techniques.
The paper tackles the problem of optimizing training convergence and generalization in deep neural networks by introducing a methodology based on the approximate Fisher information matrix, which enables dynamic tuning of mini-batch size and learning rate, resulting in faster training time and competitive accuracy compared to state-of-the-art methods.
In this paper, we introduce a novel methodology for characterising the performance of deep learning networks (ResNets and DenseNet) with respect to training convergence and generalisation as a function of mini-batch size and learning rate for image classification. This methodology is based on novel measurements derived from the eigenvalues of the approximate Fisher information matrix, which can be efficiently computed even for high capacity deep models. Our proposed measurements can help practitioners to monitor and control the training process (by actively tuning the mini-batch size and learning rate) to allow for good training convergence and generalisation. Furthermore, the proposed measurements also allow us to show that it is possible to optimise the training process with a new dynamic sampling training approach that continuously and automatically change the mini-batch size and learning rate during the training process. Finally, we show that the proposed dynamic sampling training approach has a faster training time and a competitive classification accuracy compared to the current state of the art.