Accuracy Amplification in Differentially Private Logistic Regression: A Pre-Training Approach. (arXiv:2307.13771v1 [cs.LG])

Machine learning (ML) models can memorize training datasets. As a result,
training ML models over private datasets can violate the privacy of
individuals. Differential privacy (DP) is a rigorous privacy notion to preserve
the privacy of underlying training datasets in ML models. Yet, training ML
models in a DP framework usually degrades the accuracy of ML models. This paper
aims to boost the accuracy of a DP-ML model, specifically a logistic regression
model, via a pre-training module. In more detail, …

accuracy amplification datasets differential privacy machine machine learning ml models privacy private result training