Skip to content
Skip to content
All games

Game 05 · Engine · measures: optimizers

Descent Golf

Four loss surfaces, each a specific pathology: a ravine, a curved valley, a saddle, and a bumpy basin. Pick an optimizer and a learning rate, then reach the target in as few steps as you can.

Start at the marker. Reach the target loss before the step budget runs out.

steps0/300
par35
loss1.32e+1
lr1.0e-2
statusready
How it works

Each surface has an analytic gradient, so there is no autograd and no library. SGD takes x ← x − lr·g. Momentum accumulates v ← 0.9v + g. Adam keeps the two moment estimates with bias correction, which is why it walks straight down the ravine at a learning rate that makes plain SGD oscillate out of the frame. The point of the ravine level is the condition number: the two curvatures differ by 25×, and every optimizer's behaviour on it follows from that one number.