In this paper, we compress convolutional neural network (CNN) weights post-training via
transform quantization. Previous CNN quantization techniques tend to ignore the joint …

Communicating information, like gradient vectors, between computing nodes in distributed
and federated learning is typically an unavoidable burden, resulting in scalability issues …

Recent network pruning methods focus on pruning models early-on in training. To estimate
the impact of removing a parameter, these methods use importance measures that were …

Shannon propounded a theoretical framework (collectively called information theory) that
uses mathematical tools to understand, model and analyze modern mobile wireless …

We study the neural network (NN) compression problem, viewing the tension between the
compression ratio and NN performance through the lens of rate-distortion theory. We choose …

This paper studies the fundamental limit of semantic communications over the discrete
memoryless channel. We consider the scenario to send a semantic source consisting of an …

Allocating different bit widths to different channels and quantizing them independently bring
higher quantization precision and accuracy. Most of prior works use equal bit width to …

We consider the problem of distributed feature quantization, where the goal is to enable a
pretrained classifier at a central node to carry out its classification on features that are …

It has been reported in many recent works on deep model compression that the population
risk of a compressed model can be even better than that of the original model. In this paper …

The success of deep neural networks in many real-world applications is leading to new
challenges in building more efficient architectures. One effective way of making networks …