Private Linear

Private linear models aim to perform linear regression or classification while guaranteeing the privacy of the training data, typically using differential privacy mechanisms. Current research focuses on improving the efficiency and accuracy of differentially private algorithms for high-dimensional data, exploring techniques like objective perturbation and robust optimization methods, as well as developing efficient private model selection strategies. This field is crucial for enabling the use of sensitive data in machine learning applications while adhering to strong privacy guarantees, impacting areas like healthcare and finance where data privacy is paramount.

Papers

September 27, 2024

Differentially Private Non Parametric Copulas: Generating synthetic data with non parametric copulas under privacy guarantees
Pablo A. Osorio-Marulanda, John Esteban Castro Ramirez, Mikel Hernández Jiménez, Nicolas Moreno Reyes, Gorka Epelde Unanue
Synthetic Data Differential Privacy Synthetic Data Generation Privacy Guarantee Dimensional Copula Private Synthetic Data Generation Private Linear

April 1, 2024

SoK: A Review of Differentially Private Linear Models For High-Dimensional Data
Amol Khanna, Edward Raff, Nathan Inkawhich
Differential Privacy Narrative Review High Dimensional Data Optimization Method Linear Model Private Linear

December 31, 2023

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
Rachel Redberg, Antti Koskela, Yu-Xiang Wang
Privacy Policy Practical Application Privacy Protection Private Stochastic Gradient Descent Privacy Preserving Machine Learning Privacy Analysis Private Linear

October 11, 2023

On the Computational Complexity of Private High-dimensional Model Selection
Saptarshi Roy, Zehua Wang, Ambuj Tewari
Model Selection Computational Complexity Metropolis Hastings Approximate Differential Privacy Private Linear Private Selection

May 6, 2022

Differentially Private Generalized Linear Models Revisited
Raman Arora, Raef Bassily, Cristóbal Guzmán, Michael Menart, Enayat Ullah
Loss Function Convex Loss Private Learning Square Loss Private Linear

February 16, 2022

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
Sergey Denisov, Brendan McMahan, Keith Rush, Adam Smith, Abhradeep Guha Thakurta
Differential Privacy Stochastic Gradient Descent Differential Privacy Guarantee Private Model User Level Differential Privacy Arch Factorization Private Linear

February 15, 2022

One-bit Submission for Locally Private Quasi-MLE: Its Asymptotic Normality and Limitation
Hajime Ono, Kazuhiro Minami, Hideitsu Hino
Maximum Likelihood Local Differential Privacy Local Construction Information Theoretic Privacy One Bit Private Linear

Private Linear

Papers

Differentially Private Non Parametric Copulas: Generating synthetic data with non parametric copulas under privacy guarantees

SoK: A Review of Differentially Private Linear Models For High-Dimensional Data

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

On the Computational Complexity of Private High-dimensional Model Selection

Differentially Private Generalized Linear Models Revisited

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams

One-bit Submission for Locally Private Quasi-MLE: Its Asymptotic Normality and Limitation