AI Paper Atlas

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

Asymptotically Best Causal Effect Identification with Multi-Armed Bandits

Alan Malek, Silvia Chiappa

NeurIPS 2021 · Bandits and online learning › Multi-armed bandits · approach: Best-arm identification in linear bandits · 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
use CS-LUCB confidence-sequence best-arm identification instead of uniform sampling of estimatorsformula selection (linear model, 9 formulas) · Linear model, M=3samples to terminate: needing 34% of uniform samplesImproved
use CS-SE successive elimination instead of uniform sampling of estimatorsformula selection (linear model, 9 formulas) · Linear model, M=3samples to terminate: needing 51% of uniform samplesImproved
CS-LUCB and CS-SE vs uniform on nonlinear model with nonparametric (gradient-boosted tree) nuisance estimatorsformula selection (nonlinear model, 9 formulas) · Nonlinear model, M=3samples to terminateImproved
increase number of formulas from 9 to 65 (M from 3 to 6)CS-LUCB and CS-SE · Nonlinear model, sample complexity vs number of formulassamples to terminateImproved
increase number of formulas from 9 to 65 (M from 3 to 6)uniform sampling baseline · Nonlinear model, sample complexity vs number of formulassamples to terminateHurt

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