lasso vs. ols

For lambda = 0 lasso should give the same regression coefficients as ols but it does not... Why? [B, FitInfo]=lasso(X,y,'Lambda',0:0.01:1); B(:,1) (that corresponds to lambda = 0) should give the same results like output from regress or regstats... But it doesn't. Why?

回答(0 个)

类别

提问:

2016-10-27

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by