Know a great AI tool or AI news source? Submit it to AiByts
2 min read

Coverage Cliffs in Off-Policy Quantile Certification

We study when logged contextual-bandit data can certify an upper tail quantile for a policy selected from the same sample. We construct a PAC-Bayes Bernstein lower-confidence envelope for the target cumulative distribution function (CDF), simultaneous over a predeclared threshold grid and all…

By Pauline Bourigault, Emmanuelle BourigaultarXiv cs.LG

Read the full story

Originally published by arXiv cs.LG on Oct 19, 2026.

Read on arXiv cs.LG(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.