Tensorizing Neural Networks
This enables deployment of models on low-end devices by reducing memory usage, though it is incremental as it builds on existing compression techniques.
The paper tackles the problem of high memory demands in deep neural networks, especially for fully-connected layers, by converting dense weight matrices to the Tensor Train format, achieving up to 200,000 times compression for a layer and 7 times for the whole VGG network.
Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of the layer is preserved. In particular, for the Very Deep VGG networks we report the compression factor of the dense weight matrix of a fully-connected layer up to 200000 times leading to the compression factor of the whole network up to 7 times.