← 🟣 Machine Learning

🎛 Hyperparameter Landscape

Loss:
Step: 0
Gradient norm:
FPS:
Drag — rotate · Scroll — zoom

🎛 Hyperparameter Types and Categories

A purple bead performs gradient descent across a 3D loss landscape while learning rate, momentum, batch noise and L2 regularization — representatives of the optimization, data and regularization hyperparameter categories — reshape both the terrain and the path taken across it.

🔬 What It Demonstrates

Optimization hyperparameters (learning rate, momentum) control step size and smoothing; data hyperparameters (batch size, modeled as noise) control gradient stochasticity; regularization hyperparameters reshape the landscape itself toward convexity.

🎮 How to Use

Drag each slider and watch the bead's path change immediately: raise learning rate to see overshoot, raise momentum to see smoothing through bumps, raise noise for a jittery small-batch path, and raise regularization to flatten the valleys into a single bowl.

💡 Did You Know?

Hyperparameters can't be learned the same way as model weights, because changing them changes the shape of the loss surface itself — that's why they're tuned with grid search, random search or Bayesian optimization instead of gradient descent.