7 papers
DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton
Nour Jamoussi, Ikram Dridi, Giuseppe Serra +1
Differential privacy provides formal privacy guarantees for training neural networks on sensitive data, while Bayesian deep learning offers a principled framework for uncertainty-a…
Rate-Distortion-Perception Theory: Redefining the Fundamental Limits of Information Representation
Photios A. Stavrou, Giuseppe Serra, Marios Kountouris
Classical rate-distortion (RD) theory has long established the fundamental limits of lossy compression by quantifying the minimum number of bits required to represent a source unde…
Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learning
Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou +1
Bayesian Federated Learning (BFL) combines uncertainty modeling with decentralized training, enabling the development of personalized and reliable models under data heterogeneity a…
Information-Geometric Barycenters for Bayesian Federated Learning
Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou +1
Federated learning (FL) is a widely used and impactful distributed optimization framework that achieves consensus through averaging locally trained models. While effective, this ap…
Analyzing α-divergence in Gaussian Rate-Distortion-Perception Theory
Martha V. Sourla, Giuseppe Serra, Photios A. Stavrou +1
The problem of estimating the information rate distortion perception function (RDPF), which is a relevant information-theoretic quantity in goal-oriented lossy compression and sema…
Alternating Minimization Schemes for Computing Rate-Distortion-Perception Functions with -Divergence Perception Constraints
Giuseppe Serra, Photios A. Stavrou, Marios Kountouris
We study the computation of the rate-distortion-perception function (RDPF) for discrete memoryless sources subject to a single-letter average distortion constraint and a perception…