ACP-UCB1 achieves logarithmic upper-quantile regret in stochastic bandits by combining adaptive conformal quantile estimates with UCB-style optimism.
Machine Learning and Knowledge Discovery in Databases , series =
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
-
Conformal-Style Quantile Analyses for Stochastic Bandits
ACP-UCB1 achieves logarithmic upper-quantile regret in stochastic bandits by combining adaptive conformal quantile estimates with UCB-style optimism.