Abstention budget α in Bayesian BAI induces phase transition to exponential undetected error decay exp(-α²T/8κ_ν²) for Gaussians, with matching bounds and PGWS algorithm achieving it; frequentist setting shows no such gain.
Jeff and Fan, Weiwei and Luo, Jun , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Develops ENDS procedure using answer-wise acceptance sets, restricted GLR stopping, and answer-pitfall decomposition for ranking-and-selection with non-unique answers and non-answerable estimates.
Annealed entropic allocation is an adaptive sampling policy using an annealed weighted soft-min surrogate with saddlepoint prefactors to approximate optimal static budget allocation in ranking and selection.
citing papers explorer
-
Bayesian Best-Arm Identification with Abstention: A Polynomial-to-Exponential Phase Transition
Abstention budget α in Bayesian BAI induces phase transition to exponential undetected error decay exp(-α²T/8κ_ν²) for Gaussians, with matching bounds and PGWS algorithm achieving it; frequentist setting shows no such gain.
-
Ranking-and-Selection with Multiple Correct Answers and Non-Answerable Estimates
Develops ENDS procedure using answer-wise acceptance sets, restricted GLR stopping, and answer-pitfall decomposition for ranking-and-selection with non-unique answers and non-answerable estimates.
-
Annealed Entropic Allocation for Ranking and Selection
Annealed entropic allocation is an adaptive sampling policy using an annealed weighted soft-min surrogate with saddlepoint prefactors to approximate optimal static budget allocation in ranking and selection.