Matthew Joseph

most citedBetter Private Linear Regression Through Better Private Feature Selection

1 citations · 1 across the 1 of their papers we have counts for

collaborators

2 papers

cs.CR2025

Approximate Differential Privacy of the $ℓ_{2}$ Mechanism

Matthew Joseph, Alex Kulesza, Alexander Yu

We study the $ℓ_{2}$ mechanism for computing a $d$ -dimensional statistic with bounded $ℓ_{2}$ sensitivity under approximate differential privacy. Across a range of privacy parame…

cs.LG2023★ 1 cited

Better Private Linear Regression Through Better Private Feature Selection

Travis Dick, Jennifer Gillenwater, Matthew Joseph

Existing work on differentially private linear regression typically assumes that end users can precisely set data bounds or algorithmic hyperparameters. End users often struggle to…

Approximate Differential Privacy of the ℓ2​ Mechanism

Better Private Linear Regression Through Better Private Feature Selection

Approximate Differential Privacy of the $ℓ_{2}$ Mechanism