Home▸Data Science▸Feature Scaling Contour Race (2D): Raw, Standardized, Min-Max and Robust Gradient Descent Paths

📏 Feature Scaling Contour Race (2D): Raw, Standardized, Min-Max and Robust Gradient Descent Paths

2D contour race of gradient descent under raw, standardized, min-max and robust scaling: condition numbers, shared step size, divergence and convergence paths, with five numerical checks.

Data Science2DModerate60 FPS📱 Mobile-adapted⇄ 3D version
Feature Scaling Contour Race (2D): Raw, Standardized, Min-Max and Robust Gradient Descent Paths ↗ Open standalone
⚙ Under the hood

2D contour race of gradient descent under raw, standardized, min-max and robust scaling: condition numbers, shared step size, divergence and convergence paths, with five numerical checks.

feature scalingstandardizationgradient descentcondition numbermin-max scalerrobust scalerdata science

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

What did you find?

Add reproduction steps (optional)