From the article: "[I]t is common to present differential privacy as a property that is nice-to-have but creates a necessary trade-off with performance. However, things are different with machine learning. Differential privacy is in fact well aligned with the goals of machine learning. For instance, memorizing a particular training point—like the medical record of Jane Smith—during learning is a violation of privacy. It is also a form of overfitting and harms the model’s generalization performance for patients whose medical records are similar to Jane’s."
