Skip to yearly menu bar Skip to main content


Poster

Compression-aware Training of Deep Networks

Jose Alvarez · Mathieu Salzmann

Pacific Ballroom #139

Keywords: [ Deep Learning ] [ Supervised Deep Networks ] [ Efficient Inference Methods ] [ Efficient Training Methods ]


Abstract:

In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks. Unfortunately, the huge number of units of these networks makes them expensive both computationally and memory-wise. To overcome this, exploiting the fact that deep networks are over-parametrized, several compression strategies have been proposed. These methods, however, typically start from a network that has been trained in a standard manner, without considering such a future compression. In this paper, we propose to explicitly account for compression in the training process. To this end, we introduce a regularizer that encourages the parameter matrix of each layer to have low rank during training. We show that accounting for compression during training allows us to learn much more compact, yet at least as effective, models than state-of-the-art compression techniques.

Live content is unavailable. Log in and register to view live content