AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Choice of V for V-Fold Cross-Validation in Least-Squares Density Estimation

Sylvain Arlot, Matthieu Lerasle

JMLR 2016 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling

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
increase V from 2 to 5V-fold penalization · Setting L, Dya2ratio to oracle risk: 10.21 -> 7.47Improved
increase V from 2 to 5V-fold penalization · Setting S, Dya2ratio to oracle risk: 2.39 -> 2.16Improved
increase V from 5 to 10V-fold penalization · Setting L, Dya2ratio to oracle risk: 7.47 -> 6.89Improved
increase V from 10 to n=500V-fold penalization · Setting L, Dya2ratio to oracle risk: 6.89 -> 6.35Improved
increase V from 2 to 10V-fold cross-validation · Setting L, Dya2ratio to oracle risk: 6.41 -> 6.24No clear effect
use V-fold penalty instead of V-fold CV at V=2model selection · Setting L, Dya2ratio to oracle risk: 6.41 -> 10.21Hurt
use V-fold penalty instead of V-fold CV at V=2model selection · Setting S, Dya2ratio to oracle risk: 2.05 -> 2.39Hurt
use V-fold penalty with V=n instead of pen_dimmodel selection · Setting L, Dya2ratio to oracle risk: 8.27 -> 6.35Improved
use V-fold penalty with V=n instead of pen_dimmodel selection · Setting S, Dya2ratio to oracle risk: 3.21 -> 2.06Improved
overpenalize V-fold penalty with factor C near 2.5 (ablation)penLOO · Setting L, Dya2ratio to oracle risk: C=2.5 for L-Dya2; C=1.4 for S-Dya2Improved
overpenalize V-fold penalty with factor C near 1.4 (ablation)penLOO · Setting S, Dya2ratio to oracle risk: C=1.4 for S-Dya2Improved
use Dya2 collection instead of regular histograms (Regu) (ablation)oracle estimator · Setting Lquadratic risk x10^3: 13.4 -> 5.46Improved

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