76 citations · 139 across the 23 of their papers we have counts for
3 papers · 1 filter
Over-the-Air Federated Edge Learning with Hierarchical Clustering
Ozan Aygün, Mohammad Kazemi, Deniz Gündüz +1
We examine federated learning (FL) with over-the-air (OTA) aggregation, where mobile users (MUs) aim to reach a consensus on a global model with the help of a parameter server (PS)…
Hierarchical Over-the-Air Federated Edge Learning
Ozan Aygün, Mohammad Kazemi, Deniz Gündüz +1
Federated learning (FL) over wireless communication channels, specifically, over-the-air (OTA) model aggregation framework is considered. In OTA wireless setups, the adverse channe…
Speeding-Up Back-Propagation in DNN: Approximate Outer Product with Memory
Eduin E. Hernandez, Stefano Rini, Tolga M. Duman
In this paper, an algorithm for approximate evaluation of back-propagation in DNN training is considered, which we term Approximate Outer Product Gradient Descent with Memory (Mem-…