activity
20162024
most citedCryptographic Hardness of Learning Halfspaces with Massart Noise

5 citations · 18 across the 19 of their papers we have counts for

collaborators

19 papers

cs.CR2024

Differentially Private Ad Conversion Measurement

John Delaney, Badih Ghazi, Charlie Harrison +6

In this work, we study ad conversion measurement, a central functionality in digital advertising, where an advertiser seeks to estimate advertiser website (or mobile app) conversio…

cs.DS2024

Improved Lower Bound for Differentially Private Facility Location

Pasin Manurangsi

We consider the differentially private (DP) facility location problem in the so called super-set output setting proposed by Gupta et al. [SODA 2010]. The current best known expecte…

cs.LG2024

Training Differentially Private Ad Prediction Models with Semi-Sensitive Features

Lynn Chua, Qiliang Cui, Badih Ghazi +9

Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features. In this se…

cs.LG2023

Sparsity-Preserving Differentially Private Training of Large Embedding Models

Badih Ghazi, Yangsibo Huang, Pritish Kamath +4

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm th…

cs.DS2023

User-Level Differential Privacy With Few Examples Per User

Badih Ghazi, Pritish Kamath, Ravi Kumar +3

Previous work on user-level differential privacy (DP) [Ghazi et al. NeurIPS 2021, Bun et al. STOC 2023] obtained generic algorithms that work for various learning tasks. However, t…

cs.DS20231 cited

Hardness of Approximating Bounded-Degree Max 2-CSP and Independent Set on k-Claw-Free Graphs

Euiwoong Lee, Pasin Manurangsi

We consider the question of approximating Max 2-CSP where each variable appears in at most constraints (but with possibly arbitrarily large alphabet). There is a simple $(\frac…