Understanding Subgradients Using Examples

I recommend you watch in 1.25x or 1.5x to not waste time.

Hope you will enjoy this video. I know my voiceover is lacking some emotion but i will try my best to improve that for my next video.

Definition

... a lot of

... practice if you really need to

Of

Partial X bar okay now I'm gonna talk about some

... few more

Ryan Tibshirani @ Stats, CMU. http://www.stat.cmu.edu/~ryantibs/convexopt/

In this video we start looking at non-smooth optimization. We take a look at the subdifferential set and several

We formulate the

We show two useful properties of the function values for the

Neither the lasso nor the SVM objective function is differentiable, and we had to do some work for each to optimize

A vector beta so this is a very simplified version of the lasso but I claim that we can solve it directly

Chapter 5: Convex Numerical algorithms 5.1: The

Uh the existence of a

In order to better

... some

Nest okay so that's the outline for today

... on this