AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits

Reda Ouhamma, Rémy Degenne, Pierre Gaillard, Vianney Perchet

NeurIPS 2021 · Bandits and online learning › Multi-armed bandits · approach: Fixed-confidence versus fixed-budget identification · 0 citations (OpenAlex)

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
analyse LSA with generic index-based proof instead of original proofLSA · Thresholding bandit unit costexponent constant in loss bound: 1/16020 -> 4005 times betterImproved
analyse APT with new proofAPT · Thresholding bandit zero-one lossexponent constant in loss bound: 1/32 -> 1/4Improved
use Frank-Wolfe index F(n,x;a)=max{x,1}-log max{x,1}+log(n/a) (FWT) instead of APT indexAPT · Thresholding bandit weighted errorsbound onset (T needed)Improved
use adaptive algorithms (APT, LSA, FWT) instead of the non-adaptive oracle with uniform allocationnon-adaptive oracle · N(1,1)/N(-1,1) arms, K=100error ratio to oracleImproved
use adaptive stop-on-nonzero sampling instead of uniform allocationuniform allocation · toy problem on {0,x}expected errors: 1/2^(T/K) -> 1/2^(T/2)Improved
use FWT instead of APTAPT · mu_k=(-1)^k(k/K)^2, K=50error ratio to oracleImproved
use FWT instead of LSALSA · Thresholding bandit simulationserror ratio to oracleNo clear effect
set LSA parameter alpha to 1 instead of 1/10LSA · Thresholding bandit unit costexponent constant in loss bound: 1/16020 -> 4005 times betterImproved
sample arms near threshold less (follow oracle M-shape allocation)sequential algorithms · Thresholding banditfeasibilityHurt

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