Glossary · Math & training
Optimizer
An algorithm that transforms gradients into parameter updates. Plain stochastic gradient descent is a simple baseline; momentum, Adam, and other optimizers change the update using history or adaptive scaling. Each choice has different memory, stability, and tuning behavior.
Common confusion
The optimizer consumes gradients; backpropagation computes them.
Related terms
Browse the learning paths to see this term in context — every lesson is free to read.