35 citations · 91 across the 12 of their papers we have counts for
15 papers
Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?
Razan El Mais, Ali Chehab, Ibrahim Issa +1
Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). Many decoder-only LLMs employ…
Sibson -Mutual Information and Its Variational Representations
Amedeo Roberto Esposito, Michael Gastpar, Ibrahim Issa
Information measures can be constructed from Rényi divergences much like mutual information from Kullback-Leibler divergence. One such information measure is known as Sibson -mu…
Total Variation Meets Differential Privacy
Elena Ghazi, Ibrahim Issa
The framework of approximate differential privacy is considered, and augmented by leveraging the notion of ``the total variation of a (privacy-preserving) mechanism'' (denoted by $…
Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage
Ibrahim Issa, Amedeo Roberto Esposito, Michael Gastpar
We adopt an information-theoretic framework to analyze the generalization behavior of the class of iterative, noisy learning algorithms. This class is particularly suitable for stu…
Age Distribution in Arbitrary Preemptive Memoryless Networks
Rajai Nasser, Ibrahim Issa, Ibrahim Abou-Faycal
We study the probability distribution of age of information (AoI) in arbitrary networks with memoryless service times. A source node generates packets following a Poisson process,…
Strong Asymptotic Composition Theorems for Mutual Information Measures
Benjamin Wu, Aaron B. Wagner, Ibrahim Issa +1
We characterize the growth of the Sibson and Arimoto mutual informations and -maximal leakage, of any order that is at least unity, between a random variable and a growing set o…