Chapter 3


<br>
Jerome Friedman,  Trevor Hastie and Robert Tibshirani:
<a href="http://www-stat.stanford.edu/~hastie/Papers/glmnet.pdf">
Regularized Paths for Generalized Linear Models via Coordinate Descent.
</a>
We use coordinate descent to develop regularization paths for linear,
logistic and multinomial regression models. Our algorithms use the lasso and
"elastic net" penalties of Zou and Hastie (2005), and create the
path for a grid of values of the penalty parameter lambda. The R
package <b> glmnet </b> has been submitted to
<a href="http://cran.r-project.org/">CRAN</a>
<br>
<br>
Chapter 11
<br>
<a href="comp.pdf">
A study of the NIPS feature selection challenge
</a>

<br>
<br>

Chapter 14

<br>

       (Witten, Tibshirani, Hastie).        <a href="http://www-stat.stanford.edu/~dwitten/WittenTibsHastiePMD2008.pdf">  A penalized matrix
          decomposition, with applications to sparse canonical correlation analysis and
  principal components.</a>  To appear, Biostatistics.

<p>

This paper proposes a  novel penalized matrix
          decomposition. When applied to the covariance matrix, 
it produces a version of sparse principal components that is closely
related to the methods  described in the chapter. When applied
to the cross-products matrix, a method for  sparse canonical correlation analysis
is obtained.

<p>


<br>
<br>

Robert Tibshirani  (2009).

               <a href="http://www-stat.stanford.edu/~tibs/ftp/cus.pdf">Univariate shrinkage in the  Cox model for high dimensional data
</a>


<br>

A simple  method  for predicting survival with high-dimensional features