Efficient Deep Learning with Decorrelated Backpropagation
This addresses the problem of inefficient training for large-scale deep learning practitioners, offering a novel method that is not incremental but provides substantial improvements.
The paper tackled the high computational cost and carbon footprint of training deep neural networks by introducing decorrelated backpropagation, achieving a more than two-fold speed-up and higher test accuracy compared to standard backpropagation in deep residual networks.
The backpropagation algorithm remains the dominant and most successful method for training deep neural networks (DNNs). At the same time, training DNNs at scale comes at a significant computational cost and therefore a high carbon footprint. Converging evidence suggests that input decorrelation may speed up deep learning. However, to date, this has not yet translated into substantial improvements in training efficiency in large-scale DNNs. This is mainly caused by the challenge of enforcing fast and stable network-wide decorrelation. Here, we show for the first time that much more efficient training of deep convolutional neural networks is feasible by embracing decorrelated backpropagation as a mechanism for learning. To achieve this goal we made use of a novel algorithm which induces network-wide input decorrelation using minimal computational overhead. By combining this algorithm with careful optimizations, we achieve a more than two-fold speed-up and higher test accuracy compared to backpropagation when training several deep residual networks. This demonstrates that decorrelation provides exciting prospects for efficient deep learning at scale.