AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

On Performance Estimation in Automatic Algorithm Configuration

Shengcai Liu, Ke Tang, Yunwei Lei, Xin Yao

AAAI 2020 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 21 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
Distribute runs as evenly as possible across training instancesPerformance estimation in AAC · SATenstein-QCP, clasp-weighted-sequence, LKH-uniform-400, LKH-uniform-1000estimation errorImproved
Allocate runs greedily to instances, completing up to 5 runs on each before selecting anotherPerformance estimation in AAC · Four configuration scenariosestimation errorHurt
Select instances with replacement and run once per selected instancePerformance estimation in AAC · Four configuration scenariosestimation errorHurt
Increase the number of runs NPerformance estimation in AAC · Four configuration scenariosuniform estimation errorImproved
Increase the number of training instances KPerformance estimation in AAC · Four configuration scenariosuniform estimation errorImproved
Increase the number of considered configurations mUniform performance estimation · Four configuration scenariosuniform estimation errorHurt
Run configurations on half of the training instancesPerformance estimation in AAC · Four configuration scenariosestimation errorImproved

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