Research map / Learning theory and algorithms / Sample complexity
Revisiting Active Sequential Prediction-Powered Mean Estimation
Maria-Eleni Sfyraki, Jun-Kun Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| 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 width | Improved |
| 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 datasets | confidence interval width | No clear effect |
| replace uncertainty-mixture query policy with FTRL query policy oblivious to current covariates | active sequential mean estimator · Four datasets (politeness, wine, post-election, synthetic) | confidence interval width | No clear effect |
| use FTRL query policy instead of uniform-sampling baseline with fixed ML predictor | active sequential mean estimator · Four datasets | confidence interval width | Improved |
| compare FTRL, mixture and baseline policies on coverage of true mean | active sequential mean estimator · Politeness, wine, post-election | coverage of true mean | No clear effect |
Closest papers by meaning
- Prediction-Powered Active Testing (NeurIPS 2026 · similarity 0.87)
- Anytime-valid, Bayes-assisted, Prediction-Powered Inference (NeurIPS 2025 · similarity 0.86)
- Robust Sampling for Active Statistical Inference (NeurIPS 2025 · similarity 0.86)
- Prediction-Powered Adaptive Shrinkage Estimation (ICML 2025 · similarity 0.85)
- Active Statistical Inference (ICML 2024 · similarity 0.85)
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means (NeurIPS 2026 · similarity 0.84)
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.
