Sample complexity of adaptive statistical queries
An analyst may choose each statistical query after seeing the earlier answers. The problem asks how many independent samples a mechanism needs to answer all the queries accurately despite that feedback.
Why it matters and what counts as progress
Why it matters: The result improves the leading sample term and closes a separate space gap for frequency-moment estimation when future updates can depend on earlier answers.
What counts as progress: Sharper sample bounds should state how accuracy, failure probability, query count and domain assumptions enter. A resource guarantee should identify the model it measures.
How the problem developed
- 2014 · Development [1]
Cynthia Dwork and colleagues Established a connection between stability and statistical validity for adaptively chosen analyses.
Gemini 4 Argon Gave a statistical query mechanism with no factor on the leading term and a related robust streaming algorithm.
AI contribution
Adaptive Data Analysis with polylog Overhead, Interval Validation, and Adversarially Robust Turnstile Estimation in polylog Bits
The Gemini manuscript gives a mechanism that answers k adaptively chosen bounded statistical queries over any measurable domain. Its leading sample term is proportional to with confidence-dependent factors and no multiplier. The same manuscript supplies a finite-precision interval validator and a single-pass algorithm that estimates the second frequency moment after every integer turnstile update using times a polylogarithmic number of bits.
Sources
Publication history
Daily emails by default, only when there’s an update.