corrected_LSF

CART loss given by Equation 5. The reason for the name "theoretical cuts" is that by the strong law of large numbers CART loss We first remark that in [32] their proof of Lemma 1 in fact proves more than its statement: Lemma 1. P ( Y y | X) is bounded, we may omit the truncation operators appearing in the original statements.) B.2.1 The approximation error goes to 0 (uniformly in y) B.2.2 The estimation error goes to 0 (uniformly in y) Theorem 4, we have that for all "> 0, " The classical conformalized prediction algorithm transforms a point prediction algorithm into an algorithm that outputs prediction intervals. Even with this adjustment, it took considerably longer than the other methods. In Section 6.1, we use We have re-run the tabular experiments from Section 6.1 five times to get confidence intervals.