Chapter 02.03: Linear Models with L1 Loss

In this section, we introduce \(L1\) loss and elaborate its differences to \(L2\) loss. In addition, we explain how the choice of loss affects optimization and robustness.

Lecture video

Lecture slides

Code demo

Linear model & gradient descent

You can run the code snippets in the demos on your local machine. The corresponding Rmd version of this demo can be found here. If you want to render the Rmd files to PDF, you need the accompanying style files.

Quiz

--- shuffle_questions: false --- ## Which statements are true? - [ ] The absolute loss function is more sensitive to outliers than the quadratic loss function. - [x] Optimization of $L2$ loss is easier than of $L1$ loss.