AI Paper Atlas

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

Constrained Best Arm Identification with Tests for Feasibility

Ting Cai, Kirthevasan Kandasamy

AAAI 2026 · 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
test feasibility constraints one at a time (SAMPLE-FEASIBILITY) instead of sampling all constraints together (ablation)feasible best arm identification · synthetic and drug discovery experimentssample complexityImproved
balance performance and feasibility testing instead of feasibility-firstAlgorithm 1 vs F-first · Experiment 1 instance (b)relative number of samples: 3.13 -> 1.0Improved
balance performance and feasibility testing instead of performance-firstAlgorithm 1 vs P-first · Experiment 1 instance (a)relative number of samples: 3.09 -> 1.0Improved
use Algorithm 1 instead of the best specialized baseline on its favorable instanceAlgorithm 1 vs F-first on instance (a) · Experiment 1 instance (a)relative number of samples: 0.58 vs 1.0Hurt
use Algorithm 1 instead of P-first on instance (b)Algorithm 1 vs P-first · Experiment 1 instance (b)relative number of samples: 0.84 vs 1.0Hurt
use Algorithm 1 on mixed instance with several suboptimal arm typesAlgorithm 1 vs all baselines · Experiment 1 instance (c)relative number of samples: best baseline 2.78 -> 1.0Improved
increase number of constraints N from 2 to 64Algorithm 1 · Experiment 2sample complexityImproved
apply Algorithm 1 to real drug dosage dataAlgorithm 1 · Drug discovery (Genovese et al. 2013)sample complexityImproved
use a tighter confidence bound only for TF-LUCB-C (ablation)TF-LUCB-C · Appendix confidence bound comparisonsample complexityNo clear effect

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