Conditional validity of inductive conformal predictors
This addresses a theoretical gap in conformal prediction for researchers, but appears incremental as it builds on existing methods.
The paper tackles the limitation of inductive conformal predictors, which only ensure unconditional coverage probability, by exploring ways to achieve conditional validity, but does not report specific numerical results.
Conformal predictors are set predictors that are automatically valid in the sense of having coverage probability equal to or exceeding a given confidence level. Inductive conformal predictors are a computationally efficient version of conformal predictors satisfying the same property of validity. However, inductive conformal predictors have been only known to control unconditional coverage probability. This paper explores various versions of conditional validity and various ways to achieve them using inductive conformal predictors and their modifications.