Skip to content
AImpact
IT EN
Training Intermediate Also known as: Discesa del gradiente

Gradient Descent

An optimization algorithm that updates a model's weights in the direction that most reduces the error, one small step at a time.

ShareLinkedInX

In practice

It is the core engine behind training every modern neural network. In practice people use a variant called Adam or AdamW, which is more stable and faster. If you do not train models from scratch it is a concept to know, not a knob to turn.

Related terms

Loss Function Pretraining SFT Checkpoint

Seen in the wild

0 entries mentioning it

No archive entry mentions it explicitly. Appears in broader contexts.

← All terms