331 citations · 712 across the 75 of their papers we have counts for
7 papers · 1 filter
On the Privacy-Utility Trade-off With and Without Direct Access to the Private Data
Amirreza Zamani, Tobias J. Oechtering, Mikael Skoglund
We study an information theoretic privacy mechanism design problem for two scenarios where the private data is either observable or hidden. In each scenario, we first consider boun…
Multi-User Privacy Mechanism Design with Non-zero Leakage
Amirreza Zamani, Tobias J. Oechtering, Mikael Skoglund
A privacy mechanism design problem is studied through the lens of information theory. In this work, an agent observes useful data that is correlated with private…
Power-Estimation Trade-off of Vector-valued Witsenhausen Counterexample with Causal Decoder
Maël Le Treust, Tobias Oechtering
The vector-valued extension of the famous Witsenhausen counterexample setup is studied where the encoder, i.e. the first decision maker, non-causally knows and encodes the i.i.d. s…
An Information-Theoretic Analysis of Bayesian Reinforcement Learning
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering +1
Building on the framework introduced by Xu and Raginksy [1] for supervised learning problems, we study the best achievable performance for model-based Bayesian reinforcement learni…
Bounds for Privacy-Utility Trade-off with Per-letter Privacy Constraints and Non-zero Leakage
Amirreza Zamani, Tobias J. Oechtering, Mikael Skoglund
An information theoretic privacy mechanism design problem for two scenarios is studied where the private data is either hidden or observable. In each scenario, privacy leakage cons…
Pointwise Maximal Leakage
Sara Saeidian, Giulia Cervia, Tobias J. Oechtering +1
We introduce a privacy measure called pointwise maximal leakage, generalizing the pre-existing notion of maximal leakage, which quantifies the amount of information leaking about a…