Timeline for Why is it much quicker to compute ridge regression than regular linear regression? [duplicate]
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 12, 2022 at 22:40 | history | closed | whuber♦ regression Users with the regression badge or a synonym can single-handedly close regression questions as duplicates and reopen them as needed. | Duplicate of Why is computing ridge regression with a Cholesky decomposition much quicker than using SVD? | |
| Mar 30, 2019 at 9:00 | history | tweeted | twitter.com/StackStats/status/1111916118644539392 | ||
| Mar 29, 2019 at 14:10 | history | edited | kjetil b halvorsen♦ |
edited tags
|
|
| Mar 11, 2019 at 18:40 | review | Close votes | |||
| Mar 14, 2019 at 11:12 | |||||
| Mar 11, 2019 at 18:16 | comment | added | pighead10 | IMO the amendment to this question was sufficiently different that it required its own question which I posted here: stats.stackexchange.com/questions/396914/… | |
| Mar 11, 2019 at 17:24 | comment | added | pighead10 |
Okay, so it seems LinearRegression is using SVD to find the L2 norm. In which case my question becomes: why is computing ridge regression with cholesky quicker than with SVD? (Meta question: should I adjust my question title to reflect this?)
|
|
| Mar 11, 2019 at 17:07 | comment | added | jld |
you've got $p > n$ so the usual least squares estimator is not defined as $X^TX$ is singular. This might lead to linear_model.LinearRegression doing something different. Is this helpful? stackoverflow.com/questions/23714519/…
|
|
| Mar 11, 2019 at 16:13 | history | asked | pighead10 | CC BY-SA 4.0 |