AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Recursive Quantile Estimation: Non-Asymptotic Confidence Bounds

Likai Chen, Georg Keilbar, Wei Biao Wu

JMLR 2023 · Optimization › Nonconvex and smooth optimization · approach: Stochastic gradient last-iterate analysis

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
use successive reject instead of uniform explorationquantile best arm identification · Setting 1, n=1000regret: 0.792 -> 0.190Improved
use successive reject instead of sequential halvingquantile best arm identification · Setting 1, n=1000regret: 0.377 -> 0.190Improved
use sequential halving instead of uniform explorationquantile best arm identification · Setting 2, n=2000regret: 0.381 -> 0.099Improved
increase budget n from 1000 to 8000 for successive rejectsuccessive reject · Setting 3regret: 0.162 -> 0.000Improved
increase budget n from 1000 to 8000 for uniform explorationuniform exploration · Setting 1regret: 0.792 -> 0.133Improved
use Polyak-Ruppert averaging versus last SGD iterate for tail boundsSGD quantile estimator · t-distribution df 10, tau=0.5, n=500tail probabilityImproved

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