Orthogonalising gradients to speed up neural network optimisation
This addresses optimization efficiency for neural network training, though it appears incremental as it builds on existing gradient-based methods.
The paper tackles neural network optimization slowdown by orthogonalizing gradients to diversify learned representations, achieving a large decrease in learning time on ImageNet and CIFAR-10 while maintaining similar accuracy to SGD.
The optimisation of neural networks can be sped up by orthogonalising the gradients before the optimisation step, ensuring the diversification of the learned representations. We orthogonalise the gradients of the layer's components/filters with respect to each other to separate out the intermediate representations. Our method of orthogonalisation allows the weights to be used more flexibly, in contrast to restricting the weights to an orthogonalised sub-space. We tested this method on ImageNet and CIFAR-10 resulting in a large decrease in learning time, and also obtain a speed-up on the semi-supervised learning BarlowTwins. We obtain similar accuracy to SGD without fine-tuning and better accuracy for naïvely chosen hyper-parameters.