803 citations · 3.5k across the 244 of their papers we have counts for
5 papers · 2 filters
Free Energy Minimization: A Unified Framework for Modelling, Inference, Learning,and Optimization
Sharu Theresa Jose, Osvaldo Simeone
The goal of these lecture notes is to review the problem of free energy minimization as a unified framework underlying the definition of maximum entropy modelling, generalized Baye…
Optimizing Over-the-Air Computation in IRS-Aided C-RAN Systems
Daesung Yu, Seok-Hwan Park, Osvaldo Simeone +1
Over-the-air computation (AirComp) is an efficient solution to enable federated learning on wireless channels. AirComp assumes that the wireless channels from different devices can…
End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learning
Sangwoo Park, Osvaldo Simeone, Joonhyuk Kang
When a channel model is not available, the end-to-end training of encoder and decoder on a fading noisy channel generally requires the repeated use of the channel and of a feedback…
Cooperative Learning via Federated Distillation over Fading Channels
Jin-Hyun Ahn, Osvaldo Simeone, Joonhyuk Kang
Cooperative training methods for distributed machine learning are typically based on the exchange of local gradients or local model parameters. The latter approach is known as Fede…
Inter-Tenant Cooperative Reception for C-RAN Systems With Spectrum Pooling
Junbeom Kim, Daesung Yu, Seok-Hwan Park +2
This work studies the uplink of a multi-tenant cloud radio access network (C-RAN) system with spectrum pooling. In the system, each operator has a cloud processor (CP) connected to…