AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Revisiting Active Sequential Prediction-Powered Mean Estimation

Maria-Eleni Sfyraki, Jun-Kun Wang

ICLR 2026 · Learning theory and algorithms › Sample complexity · approach: Minimax estimation rates · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
set mixing weight lambda=1 (uniform query policy) instead of 0.5 (ablation)uncertainty/uniform mixture query policy (prior work) · Post-election survey (active mean estimation)confidence interval widthImproved
set mixing weight lambda=1 instead of 0.5 on politeness, wine and synthetic datasets (ablation)uncertainty/uniform mixture query policy (prior work) · Politeness, wine review, synthetic datasetsconfidence interval widthNo clear effect
replace uncertainty-mixture query policy with FTRL query policy oblivious to current covariatesactive sequential mean estimator · Four datasets (politeness, wine, post-election, synthetic)confidence interval widthNo clear effect
use FTRL query policy instead of uniform-sampling baseline with fixed ML predictoractive sequential mean estimator · Four datasetsconfidence interval widthImproved
compare FTRL, mixture and baseline policies on coverage of true meanactive sequential mean estimator · Politeness, wine, post-electioncoverage of true meanNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy