From: omegayen on 7 May 2010 12:59 "tibshirani tibshirani" <tibs(a)stanford.edu> wrote in message <h84tje$nr2$1(a)fred.mathworks.com>... > Now (freely) available > > Glmnet for Matlab: > > Code for fitting Lasso (L1) and elastic-net regularized generalized linear models > > > Extremely efficient procedures for fitting the entire lasso or elastic-net regularization path for linear regression, logistic and multinomial regression models. > > The algorithm uses cyclical coordinate descent in a pathwise fashion. > > Go to http://www-stat.stanford.edu/~tibs/glmnet-matlab/ > > for more detals > > sincerely > > Rob Tibshirani Thanks for providing this, I looked at the examples but was not sure. How would I solve for x in the equation Ax=b using the elastic net?
From: Hui Jiang on 7 May 2010 15:00 "omegayen " <omegayen(a)ameritech.net> wrote in message <hs1gsp$saa$1(a)fred.mathworks.com>... > "tibshirani tibshirani" <tibs(a)stanford.edu> wrote in message <h84tje$nr2$1(a)fred.mathworks.com>... > > Now (freely) available > > > > Glmnet for Matlab: > > > > Code for fitting Lasso (L1) and elastic-net regularized generalized linear models > > > > > > Extremely efficient procedures for fitting the entire lasso or elastic-net regularization path for linear regression, logistic and multinomial regression models. > > > > The algorithm uses cyclical coordinate descent in a pathwise fashion. > > > > Go to http://www-stat.stanford.edu/~tibs/glmnet-matlab/ > > > > for more detals > > > > sincerely > > > > Rob Tibshirani > > Thanks for providing this, I looked at the examples but was not sure. How would I solve for x in the equation Ax=b using the elastic net? It depends on your problem. Suppose A is nxp. If n=p you can solve it using any linear solver. If n>p you can use linear regression. If n<p or you want x to be sparse, i.e. only a few elements in x are non-zeros, you can use Lasso or elastic-net.
|
Pages: 1 Prev: shape recognition Next: Individual elements of an array with a cell array |