Learning Sparse Neural Networks through L_0 Regularization

Christos Louizos, Max Welling, Diederik P. Kingma

Feb 15, 2018 (modified: Feb 23, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: We propose a practical method for $L_0$ norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up training and inference, and (2) it can improve generalization. AIC and BIC, well-known model selection criteria, are special cases of $L_0$ regularization. However, since the $L_0$ norm of weights is non-differentiable, we cannot incorporate it directly as a regularization term in the objective function. We propose a solution through the inclusion of a collection of non-negative stochastic gates, which collectively determine which weights to set to zero. We show that, somewhat surprisingly, for certain distributions over the gates, the expected $L_0$ regularized objective is differentiable with respect to the distribution parameters. We further propose the \emph{hard concrete} distribution for the gates, which is obtained by ``stretching'' a binary concrete distribution and then transforming its samples with a hard-sigmoid. The parameters of the distribution over the gates can then be jointly optimized with the original network parameters. As a result our method allows for straightforward and efficient learning of model structures with stochastic gradient descent and allows for conditional computation in a principled way. We perform various experiments to demonstrate the effectiveness of the resulting approach and regularizer.
  • TL;DR: We show how to optimize the expected L_0 norm of parametric models with gradient descent and introduce a new distribution that facilitates hard gating.
  • Keywords: Sparsity, compression, hard and soft attention.