Tag: lasso
-
How feature size interacts with regularization
In this post we’re going to explore how estimated feature size is affected by regularization. The intuition is that the shrinkage applied by regularization will mean low amplitude features get (even more) swamped by additive noise.
-
A simple property of sparse vectors
We show that the difference of any vector that is $S$-sparse and any other vector with the same or lesser $\ell_1$ norm is $S$-dominant.