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