Adaptive Neyman allocation yields strict MSE gains over uniform sampling under variance heterogeneity at finite samples, while SARP and NARP policies achieve optimal convergence rates for joint inference-regret objectives.
Since each forced round pulls a currently least-sampled arm, afterKsuch rounds every arm that was at the minimum level at the start of the block has been incremented at least once
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benefits and Costs of Adaptive Sampling
Adaptive Neyman allocation yields strict MSE gains over uniform sampling under variance heterogeneity at finite samples, while SARP and NARP policies achieve optimal convergence rates for joint inference-regret objectives.