AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Model Selection via the VC Dimension

Merlin Mpoudeu, Bertrand Clarke

JMLR 2019 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional linear regression theory · 4 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
increase sample size from 600 to 700 with similar design points (ablation)VCD estimator · Simulated linear model p=60estimated VC dimension (true 60): 50 -> 57Improved
choose design points covering the full range [0,n] (ablation)VCD estimator · Simulated linear model p=60, n=2000estimated VC dimension (true 60): 50 -> 59Improved
use more design points over a small range instead of a wide range (ablation)VCD estimator · Simulated linear model p=60, n=2000estimated VC dimension (true 60): 59 -> 50Hurt
raise n/p towards 27 from about 10 (ablation)VCD estimator · Simulated linear models p=15 to 60discrimination between models: 10 -> 27Improved
better design points at n/p of 10 (ablation)VCD estimator · Simulated linear model n/p = 10inference qualityImproved
use VCD instead of AIC, BIC, CV, ERM1, ERM2model selection · Simulated linear models, over-sized candidatessensitivity to overfittingImproved
use supremum within each interval instead of the mean in Algorithm 1 (ablation)VCD estimator · Simulated linear modelsestimator qualityHurt
estimate VC dimension via ERM1/ERM2 instead of VCD directlymodel selection · Simulated linear models, growing p at fixed nrobustnessHurt

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