activity
20232025
most citedEvaluating Differential Privacy on Correlated Datasets Using Pointwise Maximal Leakage

3 citations · 3 across the 7 of their papers we have counts for

collaborators

7 papers

stat.ML2025

Refined PAC-Bayes Bounds for Offline Bandits

Amaury Gouverneur, Tobias J. Oechtering, Mikael Skoglund

In this paper, we present refined probabilistic bounds on empirical reward estimates for off-policy learning in bandit problems. We build on the PAC-Bayesian bounds from Seldin et…

cs.IT2025

Integrated Sensing and Communication with Distributed Rate-Limited Helpers

Yiqi Chen, Holger Boche, Tobias J. Oechtering +1

This paper studies integrated sensing and communication (ISAC) systems with two rate-limited helpers who observe the channel state sequence and the feedback sequence, respectively.…

cs.CR20253 cited

Evaluating Differential Privacy on Correlated Datasets Using Pointwise Maximal Leakage

Sara Saeidian, Tobias J. Oechtering, Mikael Skoglund

Data-driven advancements significantly contribute to societal progress, yet they also pose substantial risks to privacy. In this landscape, differential privacy (DP) has become a c…

stat.ML2025

An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces

Amaury Gouverneur, Borja Rodriguez Gálvez, Tobias Oechtering +1

This paper studies the Bayesian regret of the Thompson Sampling algorithm for bandit problems, building on the information-theoretic framework introduced by Russo and Van Roy (2015…

cs.IT2025

An Information Geometric Approach to Local Information Privacy with Applications to Max-lift and Local Differential Privacy

Amirreza Zamani, Parastoo Sadeghi, Mikael Skoglund

We study an information-theoretic privacy mechanism design, where an agent observes useful data and wants to reveal the information to a user. Since the useful data is correlat…

cs.IT2024

Improving Achievability of Cache-Aided Private Variable-Length Coding with Zero Leakage

Amirreza Zamani, Mikael Skoglund

A statistical cache-aided compression problem with a privacy constraint is studied, where a server has access to a database of files, , each of size bits and…