AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Adaptive Active Hypothesis Testing under Limited Information

Fabio Cecchi, Nidhi Hegde

NeurIPS 2017 · Learning theory and algorithms › Sample complexity · approach: Generalization and limits under data constraints

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
Adding worker-quality-aware adaptive gradient selection (IBAG) instead of Chernoff's top-two selectionactive hypothesis testing with worker labels · Scenarios 1 and 2 (simulation)sample size T*Improved
Adding quality-aware selection (IBAG) instead of Soft-Decision GBSactive hypothesis testing with heterogeneous worker quality · Scenario 3sample size T*Improved
Increasing the slack s between q_{w,j*} and alpha_w (more true skill than known bound)IBAG · Scenario A simulationsample size T*Improved
Underestimating worker quality (alpha_w = q - s) for IBAGIBAG · Scenario B simulationsample size T*No clear effect
Chernoff selection relying on top-two belief components and worker skillChernoff baseline · Scenarios 1 and 2sample size T*Hurt

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