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

Yvonne Zhou; Mingyu Liang; Ivan Brugere; Danial Dervovic; Antigoni Polychroniadou; Min Wu; Dana Dachman-Soled

2024 ICML ICML 2024

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

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Yvonne Zhou, Mingyu Liang, Ivan Brugere, Danial Dervovic, Antigoni Polychroniadou, Min Wu, Dana Dachman-Soled

Topics

Machine Learning > Core Methods > Regression Machine Learning > Optimization & Theory > Learning Theory Mathematics & Optimization > Optimization > Continuous Optimization

Keywords

excess risk synthetic data linear model lipschitz loss differentially private marginal-preserving

Download PDF