Non-Adaptive 1-Bit Mean Estimation: Minimax Rates and the Sample-Interval Tradeoff
This work identifies the minimum interval budget needed to retain the unrestricted 1-bit minimax sample rate and determines the minimax sample complexity among non-adaptive 1-bit estimators when every one-set $Q^{-1}(1)$ is restricted to a union of at most $s$ intervals.
Ivan T. Lau, Jonathan Scarlett
· 0 citations