Lecture 18 – Gradient Descent

Presented by Raguvir Kunani, Anthony D. Joseph

Content by Raguvir Kunani, Josh Hug, Joseph Gonzalez, Paul Shao

A reminder – the right column of the table below contains Quick Checks. These are not required but suggested to help you check your understanding.

Video Quick Check
18.0
Introduction and Motivating Gradient Descent.
18.1
Gradient descent in one dimension. Convexity.
18.1
18.2
Various methods of optimizing loss functions in one dimension.
18.2
18.3
Gradient descent in multiple dimensions. Interpretation of gradients.
18.3
18.4
Stochastic gradient descent (SGD). Comparison between gradient descent and SGD.
18.4