AI Paper Atlas

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

An active learning framework for multi-group mean estimation

Abdellah Aznag, Rachel Cummings, Adam N. Elmachtoub

NeurIPS 2023 · Bandits and online learning › Multi-armed bandits · approach: Bandit formulations for ML problems · 1 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
vary p-norm over 1, 2, 10, 25, +inf (ablation)Variance-UCB · Gaussian 2-group simulationregret convergence slope: -2 for finite p, -1.5 for p = +infMixed
overestimate C_T (1000 instead of 5) (ablation)Variance-UCB · Gaussian 2-group simulationregretHurt
underestimate C_T (0.001 instead of 5) (ablation)Variance-UCB · Gaussian 2-group simulationregretMixed
increase lowest standard deviation sigma_min from 0.05 to 1 (ablation)Variance-UCB · finite p (1, 2)regretImproved
increase lowest variance sigma_min (ablation)Variance-UCB · p = +infregretNo clear effect
increase number of groups G from 2 to 10 and 50 (ablation)Variance-UCB · Gaussian groupsregret: ~30, 000 for G = 10 and ~90, 000 for G = 50Hurt

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