Glossary

Gradient descent — Glossary

An optimization method that updates parameters by stepping opposite the loss gradient.

Reviewed:

Full definition

Stochastic and mini-batch gradient descent power deep learning at scale. Learning rates, momentum, and adaptive optimizers such as Adam change step behavior but remain gradient-based methods.

Related encyclopedia topic

Gradient Descent — Gradient descent optimizes model parameters by repeatedly stepping opposite the gradient of the loss, forming the backbone of modern deep learning training.

← Back to glossary · Learning hub