Osvaldo Simeone

Cooperative Learning via Federated Distillation over Fading Channels

2020 · arXiv (Cornell University)

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 Federated Learning (FL). An alternative solution with reduced communication …

Decentralized Federated Learning via SGD over Wireless D2D Networks

2020 · arXiv (Cornell University)

Federated Learning (FL), an emerging paradigm for fast intelligent acquisition at the network edge, enables joint training of a machine learning model over distributed data sets and computing resources with limited disclosure of local data. …

Multi-Cell Mobile Edge Coded Computing: Trading Communication and Computing for Distributed Matrix Multiplication

2020

A multi-cell mobile edge computing network is studied, in which each user wishes to compute the product of a user-generated data matrix with a network-stored matrix through data uploading, distributed edge computing, and output downloading. …

Black-Box and Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks.

2021 · arXiv (Cornell University)

In this paper, we consider the problem of power control for a wireless network with an arbitrarily time-varying topology, including the possible addition or removal of nodes. A data-driven design methodology that leverages graph neural …

Compressed Particle-Based Federated Bayesian Learning and Unlearning

2022 · IEEE Communications Letters

Conventional frequentist federated learning (FL) schemes are known to yield overconfident decisions. Bayesian FL addresses this issue by allowing agents to process and exchange uncertainty information encoded in distributions over the model parameters. However, this …

Adaptive and Flexible Model-Based AI for Deep Receivers in Dynamic Channels

2023 · arXiv (Cornell University)

Artificial intelligence (AI) is envisioned to play a key role in future wireless technologies, with deep neural networks (DNNs) enabling digital receivers to learn to operate in challenging communication scenarios. However, wireless receiver design poses …

Bayes2IMC: In-Memory Computing for Bayesian Binary Neural Networks

2025 · IEEE Transactions on Circuits and Systems I Regular Papers

Bayesian Neural Networks (BNNs) generate an ensemble of possible models by treating model weights as random variables. This enables them to provide superior estimates of decision uncertainty. However, implementing Bayesian inference in hardware is resource-intensive, …