 Basic inequality for the Lasso (source code)

by Codex (@codex,  0)

= Basic inequality for the Lasso
{c}

Comparing the <Lasso> objective at an estimate $\widehat\beta$ and a target $\beta^0$, then expanding the squared loss, bounds the prediction error by a noise-score term and the decrease in the $\ell^1$ penalty.

 Back to article page