Search Results for author: Thomas A. Courtade

Found 6 papers, 0 papers with code

Empirical Mean and Frequency Estimation Under Heterogeneous Privacy: A Worst-Case Analysis

no code implementations15 Jul 2024 Syomantak Chaudhuri, Thomas A. Courtade

In the former setting, the privacy demand and the user data can be arbitrarily correlated while in the latter setting, there is no correlation between the dataset and the privacy demand.

Mean Estimation Under Heterogeneous Privacy Demands

no code implementations19 Oct 2023 Syomantak Chaudhuri, Konstantin Miagkov, Thomas A. Courtade

As a consequence, users with less but differing privacy requirements are all given more privacy than they require, in equal amounts.

Mean Estimation Under Heterogeneous Privacy: Some Privacy Can Be Free

no code implementations27 Apr 2023 Syomantak Chaudhuri, Thomas A. Courtade

Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm.

Worst-case vs Average-case Design for Estimation from Fixed Pairwise Comparisons

no code implementations19 Jul 2017 Ashwin Pananjady, Cheng Mao, Vidya Muthukumar, Martin J. Wainwright, Thomas A. Courtade

We show that when the assignment of items to the topology is arbitrary, these permutation-based models, unlike their parametric counterparts, do not admit consistent estimation for most comparison topologies used in practice.

Denoising Linear Models with Permuted Data

no code implementations24 Apr 2017 Ashwin Pananjady, Martin J. Wainwright, Thomas A. Courtade

The multivariate linear regression model with shuffled data and additive Gaussian noise arises in various correspondence estimation and matching problems.

Denoising regression

Linear Regression with an Unknown Permutation: Statistical and Computational Limits

no code implementations9 Aug 2016 Ashwin Pananjady, Martin J. Wainwright, Thomas A. Courtade

Consider a noisy linear observation model with an unknown permutation, based on observing $y = \Pi^* A x^* + w$, where $x^* \in \mathbb{R}^d$ is an unknown vector, $\Pi^*$ is an unknown $n \times n$ permutation matrix, and $w \in \mathbb{R}^n$ is additive Gaussian noise.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.