Timeline for Solving Linear Regression with Fused Lasso Regularization by MLE
Current License: CC BY-SA 4.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 7, 2018 at 12:49 | vote | accept | AlexConfused | ||
| Nov 6, 2018 at 12:41 | answer | added | AlexConfused | timeline score: 0 | |
| Sep 16, 2018 at 8:40 | comment | added | Richard Hardy | Therefore, I am not sure whether the current formulation of the question quite makes sense. | |
| Sep 16, 2018 at 8:38 | comment | added | Richard Hardy | The regression problem you present defines an estimator based on a loss function that is being minimized. Meanwhile, maximum likelihood (ML) defines an estimator based on maximizing the likelihood. I do not think the two can ever coincide since ML would never yield a penalized solution such as this one. ML is not even an method for calculating parameter estimates, unlike quadratic solvers, gradient descent, Newton-Raphson etc. (I have a problem finding the right term for all of these; optimization methods, maybe?). ML tells you what you are looking for but not how to calculate it mechanically. | |
| Aug 28, 2018 at 16:30 | comment | added | jbowman | This is actually related to the penalty used by P-splines, see projecteuclid.org/download/pdf_1/euclid.ss/1038425655 (Eilers and Marx, Flexible Smoothing with B-splines and Penalties). | |
| Aug 28, 2018 at 16:15 | comment | added | AlexConfused | people.cs.vt.edu/gangwang/ccs18.pdf The mentioned paragraph on the computation is directly below equation (7) | |
| Aug 28, 2018 at 15:59 | comment | added | Sextus Empiricus | Do you have a reference to the paper? | |
| Aug 28, 2018 at 15:00 | history | tweeted | twitter.com/StackStats/status/1034455737693622276 | ||
| Aug 28, 2018 at 14:29 | history | edited | AlexConfused | CC BY-SA 4.0 |
edited body
|
| Aug 28, 2018 at 13:33 | answer | added | Sextus Empiricus | timeline score: 1 | |
| Aug 28, 2018 at 12:56 | history | edited | Richard Hardy |
edited tags
|
|
| Aug 28, 2018 at 12:55 | review | First posts | |||
| Aug 28, 2018 at 15:54 | |||||
| Aug 28, 2018 at 12:55 | history | asked | AlexConfused | CC BY-SA 4.0 |