A Albasyoni, M Safaryan, L Condat… - arXiv preprint arXiv …, 2020 - arxiv.org
Communicating information, like gradient vectors, between computing nodes in distributed and federated learning is typically an unavoidable burden, resulting in scalability issues …
ES Lubana, RP Dick - arXiv preprint arXiv:2009.11839, 2020 - arxiv.org
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 …
B Isik, T Weissman, A No - International Conference on …, 2022 - proceedings.mlr.press
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 …
L Zhou, M Motani - Foundations and Trends® in …, 2023 - nowpublishers.com
Shannon propounded a theoretical framework (collectively called information theory) that uses mathematical tools to understand, model and analyze modern mobile wireless …
D Li, J Huang, C Huang, X Qin… - Journal of …, 2023 - ieeexplore.ieee.org
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 …
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 …
OA Hanna, YH Ezzeldin, T Sadjadpour… - IEEE Journal on …, 2020 - ieeexplore.ieee.org
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 …