Pruning neural networks at initialization would enable us to find sparse...
Neural compression algorithms are typically based on autoencoders that
r...
We propose a new simple approach for image compression: instead of stori...
We introduce a method to speed up training by 2x and inference by 3x in ...
We analyze the effect of quantizing weights and activations of neural
ne...
Evaluation of Bayesian deep learning (BDL) methods is challenging. We of...