Scalable Deep Neural Networks via Low-Rank Matrix Factorization

Compressing deep neural networks (DNNs) is important for real-world applications operating on resource-constrained devices. However, it is difficult to change the model size once the training is completed, which needs re-training to configure models suitable for different devices. In this paper, we propose a novel method that enables DNNs to flexibly change their size after training. We factorize the weight matrices of the DNNs via singular value decomposition (SVD) and change their ranks according to the target size. In contrast with existing methods, we introduce simple criteria that characterize the importance of each basis and layer, which enables to effectively compress the error and complexity of models as little as possible. In experiments on multiple image-classification tasks, our method exhibits favorable performance compared with other methods.

Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks

In recent years, deep neural networks (DNNs) have been applied to various machine leaning tasks, including image recognition, speech recognition, and machine translation. However, large DNN models are needed to achieve state-of-the-art performance, exceeding the capabilities of edge devices. Model reduction is thus needed for practical use. In this paper, we point out that deep learning automatically induces group sparsity of weights, in which all weights connected to an output channel (node) are zero, when training DNNs under the following three conditions: (1) rectified-linear-unit (ReLU) activations, (2) an $L_2$-regularized objective function, and (3) the Adam optimizer. Next, we analyze this behavior both theoretically and experimentally, and propose a simple model reduction method: eliminate the zero weights after training the DNN. In experiments on MNIST and CIFAR-10 datasets, we demonstrate the sparsity with various training setups. Finally, we show that our method can efficiently reduce the model size and performs well relative to methods that use a sparsity-inducing regularizer.