A regret-minimization algorithm for online conformal prediction under adversarial semi-bandit feedback achieves long-run coverage guarantees while controlling prediction set size.
However, we further strengthen themiscoverage-firstrationale in the design of the biased gain estimator˜gt(π|Πt(πt))(Eq
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization
A regret-minimization algorithm for online conformal prediction under adversarial semi-bandit feedback achieves long-run coverage guarantees while controlling prediction set size.