An adaptive 1-bit mean estimator using sequential threshold queries achieves order-optimal sample complexity for any fixed k-th moment bound, with a necessary logarithmic penalty only when variance is finite.
F X pL`σq ą0.49. 8For ease of analysis, we assume thatλis an integer multiple ofσ. 19 On the other hand, by the “k-moment
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
-
Order-Optimal Sequential 1-Bit Mean Estimation in General Tail Regimes
An adaptive 1-bit mean estimator using sequential threshold queries achieves order-optimal sample complexity for any fixed k-th moment bound, with a necessary logarithmic penalty only when variance is finite.