Timeline for How is L1 regularization derived?
Current License: CC BY-SA 3.0
24 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 18, 2017 at 1:17 | history | edited | Chill2Macht | CC BY-SA 3.0 |
added 51 characters in body; edited title
|
| May 7, 2016 at 11:35 | history | tweeted | twitter.com/StackStats/status/728911024208945152 | ||
| May 6, 2016 at 8:01 | comment | added | Scortchi♦ | You misunderstood me. Questions should at least make sense without having to read something else (imagine the link rots). So you need to include equation (3) in your question as well as quoting from the paper or paraphrasing it to explain what equation (3) represents. (The point's moot now as @AaronVoelker has done just that in his answer.) | |
| May 6, 2016 at 5:36 | vote | accept | CommunityBot | ||
| May 6, 2016 at 5:07 | answer | added | Aaron Voelker | timeline score: 6 | |
| May 6, 2016 at 3:22 | comment | added | user98374 | @Scortchi Yes, Sir. I edited the question again. But I am confused. what Stephan asked and you are asking are in complete contradiction. He says asking for a general derivation is "too broad" and suggested me to ask any specific question from the paper i linked. You seem to suggest exactly the opposite. | |
| May 6, 2016 at 3:19 | history | edited | user98374 | CC BY-SA 3.0 |
added 441 characters in body
|
| May 5, 2016 at 10:57 | history | reopened |
Stephan Kolassa Scortchi♦ |
||
| May 5, 2016 at 10:57 | comment | added | Scortchi♦ | I've re-opened the question to expedite an answer, but note that it also needs to be edited so that it makes sense without reference to an external link. | |
| May 5, 2016 at 10:44 | comment | added | Stephan Kolassa | Thanks, it's much better now. I have upvoted the question and nominated it for reopening. If it is reopened, I'll try to take a stab at it. | |
| May 5, 2016 at 9:59 | comment | added | user98374 | edited the question @StephanKolassa | |
| May 5, 2016 at 9:58 | history | edited | user98374 | CC BY-SA 3.0 |
deleted 46 characters in body; edited title
|
| May 5, 2016 at 8:42 | comment | added | Stephan Kolassa | If you are still interested in this specific derivation, I suggest you either edit this question to clarify this, or even better, ask a new specific question. It would be good if you indicated what you tried and where specifically you are stuck. | |
| May 5, 2016 at 8:41 | comment | added | Stephan Kolassa | The question as currently posed asks about "the derivations behind regularization", and this is simply too broad. The derivation of equation (4) in the paper is proposed as an example. This is different from a question that explicitly asks about a specific derivation, which as I wrote would not be too broad. Does this explain why your question was closed as "too broad"? | |
| May 5, 2016 at 3:46 | comment | added | user98374 | @StephanKolassa I just quoted that paper as an example. I was trying to say that I went though many pages/papers online and was unable to find a easy to understand answer. Please tell me how, derivative of (3) wrt w divided (2) = (4)? and more importantly why are they doing this? | |
| May 5, 2016 at 3:41 | review | Reopen votes | |||
| May 5, 2016 at 4:27 | |||||
| May 5, 2016 at 3:39 | comment | added | user98374 | @StephanKolassa you guys are the in-charge here you can do as you seem fit. but I wonder how can a explanation behind a mathematical derivation can be put on hold stating it's too broad. guess I will never understand the stringent rules of SO. | |
| May 5, 2016 at 3:36 | comment | added | user98374 | @StephanKolassa i meant how (4) was derived from (2) and (3). Look at this paper link it's very clearly explains the concept of Gradient Descent. also here link slide no 22 it's mentioned that using Taylor series approximation regularization function is simplified. I read about taylor series and then came back to the slides and more or less go an idea of the derivation. | |
| May 5, 2016 at 3:24 | history | edited | user98374 | CC BY-SA 3.0 |
edited body
|
| May 4, 2016 at 14:07 | history | closed |
Stephan Kolassa gung - Reinstate Monica Christoph Hanck whuber♦ |
Needs more focus | |
| May 4, 2016 at 12:06 | review | Close votes | |||
| May 4, 2016 at 14:07 | |||||
| May 4, 2016 at 11:49 | comment | added | Stephan Kolassa | ... If you have specific questions about the material - like how to get from (2) to (3) in that paper - please don't hesitate to ask them here. We can and will answer well-asked specific questions, whether fundamental or advanced. | |
| May 4, 2016 at 11:48 | comment | added | Stephan Kolassa | Please don't get me wrong, but getting from (2) to (3) in the paper you linked is a very basic step in matrix algebra or OLS, so if you have problems with this, you have problems with fundamental statistics. Giving an answer that starts out at this fundamental level and gets to regularization is not a good fit to SE. I'd recommend that you look at some elementary statistics textbooks or MOOCs so you understand the matrix algebra better, then continue to regularization (this textbook is good for the lasso)... | |
| May 4, 2016 at 11:38 | history | asked | user98374 | CC BY-SA 3.0 |