Bayesian Compression for Deep Learning
This addresses the need for more efficient deep learning models, which is crucial for deployment in resource-constrained environments, representing a novel method rather than an incremental improvement.
The paper tackles the problem of compression and computational efficiency in deep learning by adopting a Bayesian approach with sparsity-inducing priors to prune networks, achieving state-of-the-art compression rates while remaining competitive in speed and energy efficiency.
Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through sparsity inducing priors we prune large parts of the network. We introduce two novelties in this paper: 1) we use hierarchical priors to prune nodes instead of individual weights, and 2) we use the posterior uncertainties to determine the optimal fixed point precision to encode the weights. Both factors significantly contribute to achieving the state of the art in terms of compression rates, while still staying competitive with methods designed to optimize for speed or energy efficiency.