Research map / Optimization / Nonconvex and smooth optimization
Recursive Quantile Estimation: Non-Asymptotic Confidence Bounds
Likai Chen, Georg Keilbar, Wei Biao Wu
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 |
|---|---|---|---|
| use successive reject instead of uniform exploration | quantile best arm identification · Setting 1, n=1000 | regret: 0.792 -> 0.190 | Improved |
| use successive reject instead of sequential halving | quantile best arm identification · Setting 1, n=1000 | regret: 0.377 -> 0.190 | Improved |
| use sequential halving instead of uniform exploration | quantile best arm identification · Setting 2, n=2000 | regret: 0.381 -> 0.099 | Improved |
| increase budget n from 1000 to 8000 for successive reject | successive reject · Setting 3 | regret: 0.162 -> 0.000 | Improved |
| increase budget n from 1000 to 8000 for uniform exploration | uniform exploration · Setting 1 | regret: 0.792 -> 0.133 | Improved |
| use Polyak-Ruppert averaging versus last SGD iterate for tail bounds | SGD quantile estimator · t-distribution df 10, tau=0.5, n=500 | tail probability | Improved |
Closest papers by meaning
- Quantile Bandits for Best Arms Identification (ICML 2021 · similarity 0.88)
- Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy (NeurIPS 2025 · similarity 0.86)
- A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis (NeurIPS 2017 · similarity 0.86)
- From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits (NeurIPS 2021 · similarity 0.85)
- Differentially Private Stochastic Convex Optimization under a Quantile Loss Function (ICML 2023 · similarity 0.85)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 2025 · 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.
