Research map / Learning theory and algorithms / Sample complexity
Small Resamples, Sharp Guarantees: Convergence Rates for Resampled Studentized Quantile Estimators
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Derives convergence rates for the m-out-of-n bootstrap applied to studentized quantile estimators, giving sharp guarantees for small-subsample resampling.
Problem
The m-out-of-n bootstrap is widely used for robust inference with heavy-tailed data, but its theoretical convergence guarantees for quantile estimators are not well understood.
Approach
Provides sharp convergence rates for resampled studentized quantile estimators under the m-out-of-n bootstrap, showing how subsample size m relative to n governs accuracy.
Experimental setup
Builds on: m-out-of-n bootstrap
Closest papers by meaning
- QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions (ICML 2025 · similarity 0.88)
- Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise (ICML 2024 · similarity 0.84)
- Phase transitions for the existence of unregularized M-estimators in single index models (ICML 2025 · similarity 0.84)
- Turnstile $\ell_p$ leverage score sampling with applications (ICML 2024 · similarity 0.84)
- Empirical Bayes Rebiasing (NeurIPS 2026 · similarity 0.84)
- Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference (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.