Learning-Augmented Private Algorithms for Multiple Quantile Release

TL;DR

This paper introduces learning-augmented private algorithms for multiple quantile release, leveraging external predictions to improve utility while maintaining differential privacy, with theoretical guarantees and empirical validation.

Contribution

It develops a novel framework applying learning-augmented algorithms to differential privacy, enabling improved accuracy for multiple quantile release using external predictions.

Findings

Error bounds scale with prediction quality

Almost matches state-of-the-art guarantees

Learning predictions reduces error significantly

Abstract

When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms with predictions) framework -- previously applied largely to improve time complexity or competitive ratios -- as a powerful way of designing and analyzing privacy-preserving methods that can take advantage of such external information to improve utility. This idea is instantiated on the important task of multiple quantile release, for which we derive error guarantees that scale with a natural measure of prediction quality while (almost) recovering state-of-the-art prediction-independent guarantees. Our analysis enjoys several advantages, including minimal assumptions about the data, a natural way of adding robustness, and the provision of useful surrogate losses for two novel ``meta" algorithms that learn predictions from other (potentially sensitive) data. We conclude with experiments on challenging tasks demonstrating that learning predictions across one or more instances can lead to large error reductions while preserving privacy.