Sam Adé Jacobs

meProp: sparsified back propagation for accelerated deep learning with reduced overfitting

Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey

Model Pruning Enables Efficient Federated Learning on Edge Devices

What is Semantic Communication? A View on Conveying Meaning in the Era of Machine Intelligence

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning

Communication quantization for data-parallel training of deep neural networks

Communication Quantization for Data-Parallel Training of Deep Neural Networks