Beyond Data Splitting: Full-Data Conformal Prediction by Differential Privacy

TL;DR

This paper introduces a privacy-preserving conformal prediction method that uses full data without splitting, leveraging differential privacy to maintain coverage and improve prediction set sharpness.

Contribution

It proposes a novel full-data conformal prediction framework that avoids data splitting by using differential privacy for stability and coverage guarantees.

Findings

Achieves sharper prediction sets than split-based private methods.

Provides a universal coverage floor under differential privacy.

Demonstrates asymptotic recovery of nominal coverage levels.

Abstract

Privacy protection and uncertainty quantification are increasingly important in data-driven decision making. Conformal prediction provides finite-sample marginal coverage, but existing private approaches often rely on data splitting, reducing the effective sample size. We propose a full-data privacy-preserving conformal prediction framework that avoids splitting. Our framework leverages stability induced by differential privacy to control the gap between in-sample and out-of-sample conformal scores, and pairs this with a conservative private quantile routine designed to prevent under-coverage. We show that a generic differential privacy guarantee yields a universal coverage floor, yet cannot generally recover the nominal $1-\alpha$ level. We then provide a refined, mechanism-specific stability analysis and yields asymptotic recovery of the nominal level. Experiments demonstrate sharper prediction sets than the split-based private baseline.