12 papers
Exact Privacy--Distortion Design of Support-Constrained Randomized Response
Amirreza Zamani, Parastoo Sadeghi, Mikael Skoglund
Full-support local randomizers can incur unnecessary reporting distortion on ordered alphabets. We study randomized response whose output is restricted to a radius- neighborhood…
Residual-Information Generalization Bounds Under Selective Privacy: Extended Version
Amirreza Zamani, Parastoo Sadeghi, Mikael Skoglund
Information-theoretic generalization bounds usually control dependence on the task sample, whereas selective privacy may constrain only a different, private coordinate. We study i.…
Sparse Kernel Mechanisms for Locally Differentially Private Discrete Channels
Amirreza Zamani, Parastoo Sadeghi, Mikael Skoglund
We study sparse locally private discrete mechanisms generated by a nonnegative kernel and an input-dependent admissible output support. The support set is intentionally small relat…
Zero-determinant Strategy for Moving Target Defense: Existence, Performance, and Computation
Zhaoyang Cheng, Guanpu Chen, Yiguang Hong +2
Moving Target Defense (MTD) is commonly formulated as a repeated security game to mitigate persistent threats. Although the strong Stackelberg equilibrium (SSE) characterizes the d…
A Hierarchical Sampling Framework for bounding the Generalization Error of Federated Learning
Dario Filatrella, Ragnar Thobaben, Mikael Skoglund
We study expected generalization bounds for the Hierarchical Federated Learning (HFL) setup using Wasserstein distance. We introduce a generalized framework in which data is sample…
Sparse Point-wise Privacy Leakage: Mechanism Design and Fundamental Limits
Amirreza Zamani, Sajad Daei, Parastoo Sadeghi +1
We study an information-theoretic privacy mechanism design problem, where an agent observes useful data that is arbitrarily correlated with sensitive data , and design discl…
Privacy-Utility Trade-offs Under Multi-Level Point-Wise Leakage Constraints
Amirreza Zamani, Parastoo Sadeghi, Mikael Skoglund
An information-theoretic privacy mechanism design is studied, where an agent observes useful data which is correlated with the private data . The agent wants to reveal the i…
An Information Geometric Approach to Fairness With Equalized Odds Constraint
Amirreza Zamani, Ayfer Özgür, Mikael Skoglund
We study the statistical design of a fair mechanism that attains equalized odds, where an agent uses some useful data (database) to solve a task . Since both and are…
On Information Theoretic Fairness With A Bounded Point-Wise Statistical Parity Constraint: An Information Geometric Approach
Amirreza Zamani, Ayfer Özgür, Mikael Skoglund
In this paper, we study an information-theoretic problem of designing a fair representation under a bounded point-wise statistical (demographic) parity constraint. More specificall…
Information-Theoretic Fairness with A Bounded Statistical Parity Constraint
Amirreza Zamani, Abolfazl Changizi, Ragnar Thobaben +1
In this paper, we study an information-theoretic problem of designing a fair representation that attains bounded statistical (demographic) parity. More specifically, an agent uses…
A Coding-Theoretic Analysis of Hyperspherical Prototypical Learning Geometry
Martin Lindström, Borja Rodríguez-Gálvez, Ragnar Thobaben +1
Hyperspherical Prototypical Learning (HPL) is a supervised approach to representation learning that designs class prototypes on the unit hypersphere. The prototypes bias the repres…
A note on generalization bounds for losses with finite moments
Borja Rodríguez-Gálvez, Omar Rivasplata, Ragnar Thobaben +1
This paper studies the truncation method from Alquier [1] to derive high-probability PAC-Bayes bounds for unbounded losses with heavy tails. Assuming that the -th moment is boun…