Machine Learning

Gradient Descent

An optimization algorithm used to minimize the error (loss) of a model by iteratively adjusting parameters in the direction that reduces the loss most quickly. It is the primary method for training machine learning models.

Why It Matters

Gradient descent is the engine that powers model training. Variants like Adam and SGD determine how quickly and effectively models learn.

Example

Imagine you are blindfolded on a hilly terrain trying to reach the lowest valley — you feel the slope under your feet and take steps downhill until you reach the bottom.

Think of it like...

Like rolling a ball down a bumpy landscape — it naturally rolls toward the lowest point, just as gradient descent moves model parameters toward the lowest error.

Related Terms