Federated Learning and Distributed Optimisation

My work in federated learning studies how data owners can train models through specified information exchange. I develop communication-efficient methods for vertical federated learning and semi-decentralised coordination, and analyse convergence under the assumptions of each algorithm.

Distributed optimisation also supports my work in estimation. This includes inference in graphical models and network localisation from measurements, with attention to non-Gaussian noise and communication constraints.

The applications include task offloading in edge systems, distributed energy markets and decomposition of the inverse-rig problem in facial animation.

Funded projects

Projects active during 2021 or later, including completed projects.

• TaRDIS (2023–2026). Task leader. Decentralised learning and task orchestration for edge systems, with use cases including satellite swarms and distributed marketplaces. Reference 101093006.
• BIGMATH (2018–2022). National principal investigator. Industrial doctoral research in optimisation, statistics and linear algebra, including facial data analysis. The University of Milan coordinated the consortium. Reference 812912.

Publications since 2021

• A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning. IEEE Transactions on Signal Processing, 2026.
• Multi-Agent Reinforcement Learning for Procurement Auctions Based Distributed Energy Market Governance. Accepted at EPIA 2026.
• Communication-Efficient Vertical Federated Learning via Compressed Error Feedback. IEEE Transactions on Signal Processing, 2025.
• Maximum likelihood localization of a network of moving agents from ranges, bearings and velocity measurements. Signal Processing, 2024.
• PeersimGym: An Environment for Solving the Task Offloading Problem with Reinforcement Learning. Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track, 2024.
• Distributed Solution of the Blendshape Rig Inversion Problem. SIGGRAPH Asia 2023 Technical Communications.
• A Multi-Token Coordinate Descent Method for Vertical Federated Learning. NeurIPS 2022 Workshop on Federated Learning.
• STRONG: Synchronous and asynchronous robust network localization, under non-Gaussian noise. Signal Processing, 2021.
• ISEE.U: Distributed online estimation and control for improved target localization accuracy. 2021.

Preprints and related manuscripts since 2021

• FAuNO: Semi-Asynchronous Federated Reinforcement Learning Framework for Task Offloading in Edge Systems. arXiv preprint, 2025.
• Modular Federated Learning: A Meta-Framework Perspective. arXiv preprint, 2025.
• ISEE.U: Distributed online active target localization with unpredictable targets. arXiv preprint, 2022.
• Decentralized EM to Learn Gaussian Mixtures from Datasets Distributed by Features. arXiv preprint, 2022.