We identify and address an overlooked challenge in the practical application of data attribution: hyperparameter tuning is tricky due to the costly evaluation metrics.

The paper generalizes the utility-first approach in differential privacy to any sequence of private estimators, incurring at most a doubling of the privacy budget and allowing for hyperparameter tuning without additional privacy cost.

Do You Really Need Public Data? Public Data Surrogates for Differential Privacy on Tabular Data