AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Cross-validation Confidence Intervals for Test Error

Pierre Bayle, Alexandre Bayle, Lucas Janson, Lester W. Mackey

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 15 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 the proposed CLT-based confidence interval instead of concentration-based intervalsRidge regression test error · FlightDelays regression experiment with standardized featuresCI width: 91 times widerImproved
Use the proposed CLT-based confidence interval instead of concentration-based intervalsRidge regression test error · FlightDelays regression experiment with unstandardized featuresCI width: 5× 10^{14} times widerImproved
Use the proposed CLT-based confidence interval instead of the compared alternativesTest error assessment · Higgs classification and FlightDelays regressionCI widthImproved
Use the proposed test instead of the compared testing proceduresAlgorithm improvement testing · Higgs classification and FlightDelays regressionpowerImproved
Use the proposed test instead of a single hold-out testAlgorithm improvement testing · Higgs classification and FlightDelays regressionpowerImproved
Use the proposed test with less stable neural networks or deeper random forestsAlgorithm improvement testing · Destabilized learning algorithmstest sizeHurt
Use the proposed LOOCV interval rather than the popular alternativesRidge regression test error · Leave-one-out cross-validationCI widthImproved
Use repeated train-validation confidence intervalsTest error assessment · Higgs classification and FlightDelays regressioncoverageHurt

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