Do I need to install anything?

No. It runs in any modern browser, free, with no account required.

For Students · Gradient Descent

Gradient Descent for a cache

Built for students learning it for a class or exam. See the concept move instead of memorizing formulas — and check your homework intuition. Simulate a cache live below — adjust the inputs and watch it respond, right in your browser.

Gradient Descent StudioLive

optimization on a loss landscape

Controls

Watch gradient descent (with momentum) roll downhill on different loss landscapes. Too high a learning rate overshoots.

Presets

Learning rate

Momentum

▶ Run in Python

Data Inspector

Surfaceripple

Step0/200

Optimizermomentum GD

Governing equation

x_{k + 1} = x_{k} - η \nabla f (x_{k}), η = 3

Reading this result: A learning rate of 3 is well matched to the curvature here: steps are large enough to make progress yet small enough to avoid overshoot, giving a smooth, roughly quadratic descent toward the minimum.

Runs locally in your browser — free forever. Scale to the cloud when reality gets heavy.

or unlock everything with Pro →

Also for:Researchers Educators Engineers Hobbyists & Makers K-12 Students First Responders General version →

More with Gradient Descent

Gradient Descent for a neural network Gradient Descent for a sorting algorithm Gradient Descent for a search tree Gradient Descent for a hash table Gradient Descent for a recommendation engine Gradient Descent for an image classifier Gradient Descent for a chatbot Gradient Descent for a pathfinding AI

Frequently asked questions

Is this good for students?: Yes — this version of "Gradient Descent for a cache" is framed for students learning it for a class or exam. See the concept move instead of memorizing formulas — and check your homework intuition.
Do I need to install anything?: No. It runs in any modern browser, free, with no account required.