Beyond Data Splitting: Full-Data Conformal Prediction by Differential Privacy
This work addresses the problem of maintaining high predictive accuracy while ensuring privacy and uncertainty quantification for data-driven decision-making, which is crucial for applications where data splitting is prohibitive or leads to reduced performance.
This paper introduces a full-data privacy-preserving conformal prediction framework that avoids data splitting. It leverages differential privacy to control the gap between in-sample and out-of-sample conformal scores and uses a conservative private quantile routine, resulting in sharper prediction sets compared to split-based private baselines.
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 $1-α$ 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.