6 papers
SPARQ: An Optimization Framework for the Distribution of AI-Intensive Applications under Non-Linear Delay Constraints
Pietro Spadaccino, Paolo Di Lorenzo, Sergio Barbarossa +2
Next-generation real-time compute-intensive applications, such as extended reality, multi-user gaming, and autonomous transportation, are increasingly composed of heterogeneous AI-…
Frame-Based Zero-Shot Semantic Channel Equalization for AI-Native Communications
Simone Fiorellino, Claudio Battiloro, Emilio Calvanese Strinati +1
In future AI-native wireless networks, the presence of mismatches between the latent spaces of independently designed and trained deep neural network (DNN) encoders may impede mutu…
Over-the-Air Edge Inference via End-to-End Metasurfaces-Integrated Artificial Neural Networks
Kyriakos Stylianopoulos, Paolo Di Lorenzo, George C. Alexandropoulos
In the Edge Inference (EI) paradigm, where a Deep Neural Network (DNN) is split across the transceivers to wirelessly communicate goal-defined features in solving a computational t…
Topological Dictionary Learning
Enrico Grimaldi, Claudio Battiloro, Paolo Di Lorenzo
The aim of this paper is to introduce a novel dictionary learning algorithm for sparse representation of signals defined over combinatorial topological spaces, specifically, regula…
Learning Multi-Frequency Partial Correlation Graphs
Gabriele D'Acunto, Paolo Di Lorenzo, Francesco Bonchi +2
Despite the large research effort devoted to learning dependencies between time series, the state of the art still faces a major limitation: existing methods learn partial correlat…
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…