Timeline for Noise in regression problems and ways to reduce it
Current License: CC BY-SA 4.0
25 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 31, 2022 at 19:15 | vote | accept | Rodvi | ||
| Jan 31, 2022 at 9:32 | history | edited | Rodvi | CC BY-SA 4.0 |
some clarification
|
| Dec 6, 2021 at 5:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Aug 4, 2021 at 23:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Apr 6, 2021 at 12:08 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Dec 5, 2020 at 7:06 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| S Nov 4, 2020 at 16:03 | history | bounty ended | CommunityBot | ||
| S Nov 4, 2020 at 16:03 | history | notice removed | CommunityBot | ||
| Nov 3, 2020 at 17:44 | history | edited | Rodvi | CC BY-SA 4.0 |
clarifying the problem
|
| Nov 3, 2020 at 17:42 | comment | added | Rodvi | @markowitz Maybe this explanation will give you better understanding of my point of view. | |
| Nov 3, 2020 at 17:13 | answer | added | Rodvi | timeline score: 1 | |
| Nov 3, 2020 at 13:17 | comment | added | markowitz | Your definition of “noise” can be used also for something like MSE around a prediction. Moreover you speak about train and test sets there. I read the rest also. However until now I remain dubious about what do you mean. | |
| Nov 3, 2020 at 13:05 | comment | added | Rodvi | @markowitz sorry, word "training" is unnecessary in my comment, I mean any finite sets from distribution $\tilde p(\tilde x, \tilde y)$ (which are not necessary used for training). Because there is no any learning algorithms at all in the expression for the noise, we can treat it completely independently of them (noise is defined only by distribution). I hope my question post is clear enough to understand that I mean. | |
| Nov 3, 2020 at 12:45 | comment | added | markowitz | Well, so written it seem that you are focused on training error. True error is not an “empirical quantity” estimated on a finite sample. So, bring towards zero the training error is an easy task. | |
| Nov 3, 2020 at 12:12 | comment | added | Rodvi | @markowitz I am interested in improving empirical estimates of the noise term (we can calculate these empirical estimates using finite training sets). I am not interested in general EPE minimization, since it can be done using bias or variance reduction. | |
| Nov 3, 2020 at 12:03 | comment | added | markowitz | @Rodvi; You talk about bias-variance tradeoff. It refers on Expected Prediction Error (=EPE). Prediction error can be also translate in “test error”. Your “noise” stand for test error? Are you interested in EPE minimization? | |
| Nov 2, 2020 at 11:02 | history | edited | Rodvi | CC BY-SA 4.0 |
little correction
|
| Nov 2, 2020 at 0:00 | history | tweeted | twitter.com/StackStats/status/1323052235157344256 | ||
| Nov 1, 2020 at 23:06 | comment | added | cure | Fixed $x$ has meaning in regression analysis. Quite clear and historical explanations why to do so provide B.Chen and J.Pearl in "Regression and Causation: A Critical Examination of Six Econometrics Textbooks". | |
| Nov 1, 2020 at 22:32 | answer | added | Aram | timeline score: 1 | |
| S Oct 27, 2020 at 14:41 | history | bounty started | Rodvi | ||
| S Oct 27, 2020 at 14:41 | history | notice added | Rodvi | Draw attention | |
| Oct 27, 2020 at 14:39 | history | edited | Rodvi |
added tag
|
|
| Oct 23, 2020 at 17:08 | history | edited | Rodvi | CC BY-SA 4.0 |
added some details for fixed X
|
| Oct 23, 2020 at 8:51 | history | asked | Rodvi | CC BY-SA 4.0 |