A regret-minimization algorithm for online conformal prediction under adversarial semi-bandit feedback achieves long-run coverage guarantees while controlling prediction set size.
Then, for each π∈Π , the following holds with probability at least1−δ: TX t=1 gt(π)≤ TX t=1 ˜gt(π|Πt(πt)) + ln(δ−1) β
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.