What is Gradient Descent?

What is Gradient Descent?

Approach: Describe the iterative optimization algorithm for finding a local minimum.

An optimization algorithm used to minimize a loss function by iteratively moving in the direction of the steepest descent, defined by the negative of the gradient. The step size is determined by the learning rate.

Follow-up: What happens if the learning rate is too high?

Key concepts: learning rate, convergence, partial derivatives.