Back to Search Start Over

Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data

Authors :
Zhou, Yvonne
Liang, Mingyu
Brugere, Ivan
Dachman-Soled, Dana
Dervovic, Danial
Polychroniadou, Antigoni
Wu, Min
Publication Year :
2024

Abstract

The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To prevent leakage of sensitive data, we consider using differentially-private (DP), synthetic training data instead of real training data to train an ML model. A key desirable property of synthetic data is its ability to preserve the low-order marginals of the original distribution. Our main contribution comprises novel upper and lower bounds on the excess empirical risk of linear models trained on such synthetic data, for continuous and Lipschitz loss functions. We perform extensive experimentation alongside our theoretical results.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2402.04375
Document Type :
Working Paper