1 code implementation • 23 Feb 2024 • Hrad Ghoukasian, Shahab Asoodeh
In this work, we investigate binary classification under the constraints of both differential privacy and fairness.
no code implementations • 9 Dec 2023 • Alireza F. Pour, Hassan Ashtiani, Shahab Asoodeh
Namely, it breaks the known lower bound of $\Omega\left(\frac{k\log k}{\alpha^2\min \{ \varepsilon^2 , 1\}} \right)$ for the sample complexity of non-interactive hypothesis selection.
no code implementations • 17 May 2023 • Shahab Asoodeh, Mario Diaz
The Noisy-SGD algorithm is widely used for privately training machine learning models.
no code implementations • 24 Oct 2022 • Shahab Asoodeh, Huanyu Zhang
We investigate the contraction properties of locally differentially private mechanisms.
no code implementations • 20 Aug 2022 • Wael Alghamdi, Shahab Asoodeh, Flavio P. Calmon, Juan Felipe Gomez, Oliver Kosut, Lalitha Sankar, Fei Wei
SPA approximates privacy guarantees for the composition of DP mechanisms in an accurate and fast manner.
no code implementations • 25 Jun 2022 • Wael Alghamdi, Shahab Asoodeh, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar, Fei Wei
Since the optimization problem is infinite dimensional, it cannot be solved directly; nevertheless, we quantize the problem to derive near-optimal additive mechanisms that we call "cactus mechanisms" due to their shape.
1 code implementation • 15 Jun 2022 • Wael Alghamdi, Hsiang Hsu, Haewon Jeong, Hao Wang, P. Winston Michalak, Shahab Asoodeh, Flavio P. Calmon
We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks.
no code implementations • 2 Feb 2021 • Shahab Asoodeh, Maryam Aliakbarpour, Flavio P. Calmon
We investigate the local differential privacy (LDP) guarantees of a randomized privacy mechanism via its contraction properties.
no code implementations • 20 Dec 2020 • Shahab Asoodeh, Mario Diaz, Flavio P. Calmon
First, it implies that local differential privacy can be equivalently expressed in terms of the contraction of $E_\gamma$-divergence.
no code implementations • 12 Nov 2020 • Shahab Asoodeh, Flavio Calmon
Information bottleneck (IB) and privacy funnel (PF) are two closely related optimization problems which have found applications in machine learning, design of privacy algorithms, capacity problems (e. g., Mrs. Gerber's Lemma), strong data processing inequalities, among others.
no code implementations • 14 Aug 2020 • Shahab Asoodeh, Jiachun Liao, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar
In the first part, we develop a machinery for optimally relating approximate DP to RDP based on the joint range of two $f$-divergences that underlie the approximate DP and RDP.
no code implementations • 17 Jan 2020 • Shahab Asoodeh, Mario Diaz, Flavio P. Calmon
We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens.
no code implementations • 16 Jan 2020 • Shahab Asoodeh, Jiachun Liao, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar
We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R\'enyi differential privacy (RDP).
no code implementations • 17 Oct 2019 • Hsiang Hsu, Shahab Asoodeh, Flavio du Pin Calmon
The core of this mechanism relies on a data-driven estimate of the trimmed information density for which we propose a novel estimator, named the trimmed information density estimator (TIDE).
no code implementations • 25 Sep 2019 • Naganand Yadati, Tingran Gao, Shahab Asoodeh, Partha Talukdar, Anand Louis
In this paper, we explore GNNs for graph-based SSL of histograms.
no code implementations • 6 Sep 2018 • Tingran Gao, Shahab Asoodeh, Yi Huang, James Evans
Inspired by recent interests of developing machine learning and data mining algorithms on hypergraphs, we investigate in this paper the semi-supervised learning algorithm of propagating "soft labels" (e. g. probability distributions, class membership scores) over hypergraphs, by means of optimal transportation.
no code implementations • 9 Apr 2018 • Shahab Asoodeh, Yi Huang, Ishanu Chattopadhyay
We investigate the problem of reliable communication between two legitimate parties over deletion channels under an active eavesdropping (aka jamming) adversarial model.
no code implementations • 22 Mar 2018 • Shahab Asoodeh, Tingran Gao, James Evans
We introduce a novel definition of curvature for hypergraphs, a natural generalization of graphs, by introducing a multi-marginal optimal transport problem for a naturally defined random walk on the hypergraph.
no code implementations • 16 Feb 2018 • Hsiang Hsu, Shahab Asoodeh, Salman Salamatian, Flavio P. Calmon
Given a pair of random variables $(X, Y)\sim P_{XY}$ and two convex functions $f_1$ and $f_2$, we introduce two bottleneck functionals as the lower and upper boundaries of the two-dimensional convex set that consists of the pairs $\left(I_{f_1}(W; X), I_{f_2}(W; Y)\right)$, where $I_f$ denotes $f$-information and $W$ varies over the set of all discrete random variables satisfying the Markov condition $W \to X \to Y$.
no code implementations • 7 Nov 2015 • Shahab Asoodeh, Mario Diaz, Fady Alajaji, Tamás Linder
To this end, the so-called {\em rate-privacy function} is introduced to quantify the maximal amount of information (measured in terms of mutual information) that can be extracted from $Y$ under a privacy constraint between $X$ and the extracted information, where privacy is measured using either mutual information or maximal correlation.