research
∙
05/17/2023
Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses
The Noisy-SGD algorithm is widely used for privately training machine le...
share
research
∙
05/11/2023
The Cardinality Bound on the Information Bottleneck Representations is Tight
The information bottleneck (IB) method aims to find compressed represent...
research
∙
10/24/2022
Contraction of Locally Differentially Private Mechanisms
We investigate the contraction properties of locally differentially priv...
research
∙
08/20/2022
The Saddle-Point Accountant for Differential Privacy
We introduce a new differential privacy (DP) accountant called the saddl...
research
∙
06/25/2022
Cactus Mechanisms: Optimal Differential Privacy Mechanisms in the Large-Composition Regime
Most differential privacy mechanisms are applied (i.e., composed) numero...
research
∙
06/15/2022
Beyond Adult and COMPAS: Fairness in Multi-Class Prediction
We consider the problem of producing fair probabilistic classifiers for ...
research
∙
02/02/2021
Local Differential Privacy Is Equivalent to Contraction of E_γ-Divergence
We investigate the local differential privacy (LDP) guarantees of a rand...
research
∙
12/20/2020
Privacy Analysis of Online Learning Algorithms via Contraction Coefficients
We propose an information-theoretic technique for analyzing privacy guar...
research
∙
11/12/2020
Bottleneck Problems: Information and Estimation-Theoretic View
Information bottleneck (IB) and privacy funnel (PF) are two closely rela...
research
∙
08/14/2020
Three Variants of Differential Privacy: Lossless Conversion and Applications
We consider three different variants of differential privacy (DP), namel...
research
∙
07/18/2020
Differentially Private Mechanisms for Count Queries
In this paper, we consider the problem of responding to a count query (o...
research
∙
01/17/2020
Privacy Amplification of Iterative Algorithms via Contraction Coefficients
We investigate the framework of privacy amplification by iteration, rece...
research
∙
01/16/2020
A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences
We derive the optimal differential privacy (DP) parameters of a mechanis...
research
∙
10/17/2019
Obfuscation via Information Density Estimation
Identifying features that leak information about sensitive attributes is...
research
∙
09/06/2018
Wasserstein Soft Label Propagation on Hypergraphs: Algorithm and Generalization Error Bounds
Inspired by recent interests of developing machine learning and data min...
research
∙
04/09/2018
A Tamper-Free Semi-Universal Communication System for Deletion Channels
We investigate the problem of reliable communication between two legitim...
research
∙
03/22/2018
Curvature of Hypergraphs via Multi-Marginal Optimal Transport
We introduce a novel definition of curvature for hypergraphs, a natural ...
research
∙
02/16/2018
Generalizing Bottleneck Problems
Given a pair of random variables (X,Y)∼ P_XY and two convex functions f_...
research
∙
01/10/2018
On the Noise-Information Separation of a Private Principal Component Analysis Scheme
In a survey disclosure model, we consider an additive noise privacy mech...
research
∙
11/07/2015