GRADIENT DESCENT EXPLORER
The optimizer is the same point in both views: height is loss in 3D, while the contour map exposes direction and path shape in 2D.
ready
3D loss surface · drag to orbit
2D contour map · drag starting point
Iteration0
Position (x, y)
Loss
Gradient magnitude
Try it: raise the learning rate until the path crosses the ravine, then add momentum and watch the oscillation change.
current pointoptimization pathlower loss