Cross-Validation From Scratch and a Surprise at n=100
Textbooks say LOOCV has the lowest bias but highest variance compared to 10 and 5-fold. Coded a K-Fold CV from scratch for learning to test that on simulated data 🔍📊 — and at n=1000 it holds up. At n=100? Not so much. 🤔
Summary
The author tests K-Fold Cross-Validation against Leave-One-Out Cross-Validation using simulated data, revealing surprising performance differences at smaller sample sizes. This analysis highlights how traditional expectations about bias and variance may not hold true in practice.
Comments (0 of ) ⌛