Batch Size Scaling

How models actually learn, from vanilla gradient descent to Adam

Batch size, written B, changes the noise in gradient estimates. A small batch gives a noisy but cheap estimate. A large batch gives a steadier estimate, but each update costs more.

🔒 This is a Pro lesson — the interactive figure, worked examples, quiz and practice open with Pro access.

▶ Batch Size Scaling
← Mixed Precision & Loss ScalingGradient Accumulation →