The paper proves that deterministic FDR-controlling procedures incur linear regret in online multiple testing and introduces DOMT, a perturbation-based meta-wrapper that reduces regret to order-optimal sublinear levels while preserving safety.
stochastic tunneling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Regret Perspective on Online Multiple Testing
The paper proves that deterministic FDR-controlling procedures incur linear regret in online multiple testing and introduces DOMT, a perturbation-based meta-wrapper that reduces regret to order-optimal sublinear levels while preserving safety.