Splitting Steepest Descent for Growing Neural Architectures

Part of Advances in Neural Information Processing Systems 32 (NeurIPS 2019)

AuthorFeedback Bibtex MetaReview Metadata Paper Reviews Supplemental


Lemeng Wu, Dilin Wang, Qiang Liu


We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs. By leveraging a functional steepest descent idea, we derive a simple criterion for deciding the best subset of neurons to split and a \emph{splitting gradient} for optimally updating the off-springs. Theoretically, our splitting strategy is a second order functional steepest descent for escaping saddle points in an $\Linfty$-Wasserstein metric space, on which the standard parametric gradient descent is a first-order steepest descent. Our method provides a new computationally efficient approach for optimizing neural network structures, especially for learning lightweight neural architectures in resource-constrained settings.