Predictive Inference with Feature Conformal Prediction

Understand

Conformal prediction is a distribution-free technique for establishing valid prediction intervals.

• Although conventionally people conduct conformal prediction in the output space, this is not the only possibility.
• In this paper, we propose feature conformal prediction, which extends the scope of conformal prediction to semantic feature spaces by leveraging the inductive bias of deep representation learning.
• From a theoretical perspective, we demonstrate that feature conformal prediction provably outperforms regular conformal prediction under mild assumptions.