5 papers · 1 filter
Information Bottleneck Meets Quantization: Finite Rate Analysis and Optimal Designs
Francesco Binucci, Paolo Banelli
The Information Bottleneck (IB) is a well established framework that looks for a latent compact representation of a data source, by trading rate and data-size representation, for i…
Radio-Coverage-Aware Path Planning for Cooperative Autonomous Vehicles
Giuseppe Baruffa, Luca Rugini, Francesco Binucci +3
Fleets of autonomous vehicles (AV) often are at the core of intelligent transportation scenarios for smart cities, and may require a wireless Internet connection to offload compute…
Conformal Lyapunov Optimization: Optimal Resource Allocation under Deterministic Reliability Constraints
Francesco Binucci, Osvaldo Simeone, Paolo Banelli
This paper introduces conformal Lyapunov optimization (CLO), a novel resource allocation framework for networked systems that optimizes average long-term objectives, while satisfyi…
Opportunistic Information-Bottleneck for Goal-oriented Feature Extraction and Communication
Francesco Binucci, Paolo Banelli, Paolo Di Lorenzo +1
The Information Bottleneck (IB) method is an information theoretical framework to design a parsimonious and tunable feature-extraction mechanism, such that the extracted features a…
Enabling Edge Artificial Intelligence via Goal-oriented Deep Neural Network Splitting
Francesco Binucci, Mattia Merluzzi, Paolo Banelli +2
Deep Neural Network (DNN) splitting is one of the key enablers of edge Artificial Intelligence (AI), as it allows end users to pre-process data and offload part of the computationa…