Skip to main content
Interactive 3D/Optimizer Race
S = start ยท green ring = global minimum at (1,1)
Optimizers
Learning Rate
lr = 0.0100
0.0010.05
Max Iterations
iter = 500
1002000
Controls
Current Status
iter: 0/500
SGD:6.5625
Momentum:6.5625
RMSProp:6.5625
Adam:6.5625
Key Insight
Adam wins on most surfaces: it adapts the lr per-parameter. SGD is slow but sometimes generalises better. The Rosenbrock valley is intentionally hard - flat in one direction, steep in the other.
Try: lr=0.001 - SGD barely moves. Increase to 0.01 and watch Adam sprint while Momentum builds speed gradually.

Optimizer Race - Interactive Visualization

Modern ML uses Adam, not plain SGD - but why? This visualization races SGD, Momentum, RMSProp, and Adam from the same starting point on a challenging loss surface contour plot. Adam reaches the minimum fastest by maintaining per-parameter learning rates and first/second moment estimates. Momentum overshoots and oscillates. Plain SGD trudges along slowly, often following a zigzag path.

  • Watch SGD, Momentum, RMSProp, and Adam race to minimum simultaneously
  • See color-coded paths on the loss contour map
  • Adjust learning rate to see all methods affected differently
  • Understand why adaptive methods (Adam, RMSProp) are preferred
  • See Momentum overshooting and SGD zigzagging vs Adam's smooth path

Part of the EngineersOfAI Interactive 3D - free interactive visualizations covering every major concept in machine learning and AI engineering. Hover any element for a plain-English explanation. No code required.