AI Paper Atlas

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

Active Learning with Safety Constraints

Romain Camilleri, Andrew Wagenmaker, Jamie Heather Morgenstern, Lalit K Jain, Kevin Jamieson

NeurIPS 2022 · Bandits and online learning › Multi-armed bandits · approach: Pure exploration algorithms · 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
Use adaptive experimental design that balances safety-gap and optimality-gap estimationBeside · Multi-Armed Banditsample complexity: up to about two timesImproved
Use adaptive experimental design that balances safety and optimality estimationBeside · Linear Response Model, random instancesample complexityImproved
Combine safety-focused and difference-focused designs rather than using only XYdiffBeside · Linear Response Model, hard instancesample complexityImproved
Use randomized active exploration and safety/difference-focused sampling instead of passive uniform samplingConstrained classification · AdultFDRImproved
Use randomized active exploration and safety/difference-focused sampling instead of passive uniform samplingConstrained classification · AdultaccuracyImproved
Use active sampling rather than passive uniform samplingConstrained classification · Adultlabels needed for a given FDR: half the number of samplesImproved
Use randomized active exploration and safety/difference-focused sampling instead of passive uniform samplingConstrained classification · German CreditTPRImproved
Use randomized active exploration and safety/difference-focused sampling instead of passive uniform samplingConstrained classification · German CreditprecisionImproved
Use active sampling rather than passive uniform samplingConstrained classification · German Creditlabels needed for a given precision: half the number of samplesImproved

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