23 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…
Neilson's Weak vs. Strong Loss Aversion: A Characterization and a Generalized CPT-Utility Function
Symeon Vaidanis, Marios Kountouris
In multi-objective and multi-criteria decision-making under risk, especially in settings involving individual behavior, risk-aware analysis based on subjective evaluation has becom…
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…
Sequential Fairness Auditing with Limited Output Access
Ioannis Pitsiorlas, Martha V. Sourla, Marios Kountouris
External evaluations are becoming increasingly central to the governance of AI systems. In practice, however, independent auditors often have limited access to deployed models and…
Probabilistic Risk Sensitivity and Loss Aversion in Cumulative Prospect Theory
Symeon Vaidanis, Marios Kountouris
This paper develops a binary-gamble framework for characterizing risk sensitivity and loss aversion in Cumulative Prospect Theory (CPT). The proposed probabilistic risk-sensitivity…
Copula-Induced Correntropy for Robust Conjugate Gradient Learning
Farshad Rostami Ghadi, F. Javier Lopez-Martinez, David Morales-Jimenez +2
Robust learning in the presence of non-Gaussian and statistically dependent noise remains a fundamental challenge in signal processing and adaptive systems. Although information-th…