Research map / Learning theory and algorithms / Sample complexity
Tight Asymptotics of Extreme Order Statistics
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.
Studies the asymptotic behavior of extreme order statistics of many i.i.d. samples from a distribution with finite expectation, motivated by robust learning, bandits, and auction revenue estimation.
Problem
Asymptotic behavior of order statistics (especially extremes) of a large number of independent samples from a distribution with finite expectation, which underlies problems in robust learning under adversarial noise, best-arm identification, and second-price auction revenue estimation.
Approach
Derives tight asymptotics for extreme order statistics under only a finite-expectation assumption; the abstract is truncated so the specific technique is not stated.
Closest papers by meaning
- On the Asymptotic Distribution of the Minimum Empirical Risk (ICML 2024 · similarity 0.82)
- Asymptotic Anytime-Valid Inference for U-statistics (NeurIPS 2026 · similarity 0.81)
- Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference (NeurIPS 2026 · similarity 0.81)
- Phase transitions for the existence of unregularized M-estimators in single index models (ICML 2025 · similarity 0.81)
- Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits (NeurIPS 2026 · similarity 0.80)
- Mean Testing under Truncation beyond Gaussian (NeurIPS 2026 · similarity 0.80)
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.