Home▸Machine Learning & Neural Networks▸CMA-ES 2D: Covariance Adaptation on a Loss Contour Map

CMA-ES 2D: Covariance Adaptation on a Loss Contour Map

A top-down, independently-computed CMA-ES optimizer: watch the sampling ellipse stretch and rotate over a live contour map (Sphere, Rosenbrock, Rastrigin) with a real-time convergence chart alongside.

Machine Learning & Neural Networks2DAdvanced60 FPS📱 Mobile-adapted⇄ 3D version

This is the 2D companion to the 3D CMA-ES landscape simulator: the same real update equations — weighted-mean recombination, rank-1 and rank-μ covariance adaptation, and cumulative step-size control — run independently here over a top-down contour map (Sphere, Rosenbrock or Rastrigin), with a live convergence chart tracking best fitness and step size alongside. Pan and zoom the contour map, toggle covariance/step-size adaptation on or off, and watch the sampling ellipse stretch, rotate and shrink toward the optimum generation by generation.

⚙ Under the hood

A top-down, independently-computed CMA-ES optimizer: pan and zoom a live contour map (Sphere, Rosenbrock, Rastrigin) as the sampling ellipse stretches and rotates, with a real-time log-scale chart tracking best fitness and step size alongside. Toggle covariance and step-size adaptation on or off to compare against isotropic search.

cma-esevolution-strategyhyperparameter-optimizationblack-box-optimizationgaussian-processmachine-learning

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