Home▸Data Science▸Bias-Variance Decomposition of Polynomial Regression: Underfitting, Overfitting and Test Error (2D)

Bias-Variance Decomposition of Polynomial Regression: Underfitting, Overfitting and Test Error (2D)

Polynomial fits to repeated noisy training sets, with the exact bias and variance curves and Blender-rendered desk props. The same shared model as the 3D board.

Data Science2DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 3D version
Bias-Variance Decomposition of Polynomial Regression: Underfitting, Overfitting and Test Error (2D) ↗ Open standalone

Fit polynomials of any degree to noisy samples of a sine and see the expected test error split exactly into squared bias, variance and irreducible noise. Grey curves are earlier training sets, the yellow curve is the mean fit. A Blender-built data board with six independent numerical checks (Monte Carlo, hat-matrix trace, orthogonality, interpolation).

⚙ Under the hood

Polynomial fits to repeated noisy training sets, with the exact bias and variance curves and Blender-rendered desk props. The same shared model as the 3D board.

Bias-VariancePolynomial RegressionOverfittingUnderfittingTest Error

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)