Timeline for Is it true that Bayesian methods don't overfit?
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 5 at 17:17 | comment | added | Durden | Your example of a posterior "reverting" to the prior is known as posterior collapse. It's not a bug of the Bayesian method but rather an indication of insufficient information in your sample (at least for parts of your model). In a non-Bayesian setting your model would simply be unidentified. | |
| May 5, 2019 at 13:49 | comment | added | probabilityislogic | was just thinking - is there a mathematically precise way you can define "over fitting"? if you can, it is likely you can also build features into a likelihood function or a prior to avoid it happening. my thinking is that this notion sounds similar to "outliers". | |
| Apr 25, 2017 at 15:39 | history | edited | kjetil b halvorsen♦ |
edited tags
|
|
| Mar 6, 2017 at 22:46 | history | edited | MWB | CC BY-SA 3.0 |
added 1 character in body
|
| Mar 6, 2017 at 14:56 | vote | accept | MWB | ||
| Mar 4, 2017 at 18:33 | answer | added | Matthew Gunn | timeline score: 21 | |
| Mar 4, 2017 at 3:10 | history | tweeted | twitter.com/StackStats/status/837862897577517056 | ||
| Mar 3, 2017 at 22:54 | answer | added | Dave Harris | timeline score: 33 | |
| Mar 2, 2017 at 23:18 | history | edited | MWB | CC BY-SA 3.0 |
added 16 characters in body
|
| Mar 2, 2017 at 21:51 | history | asked | MWB | CC BY-SA 3.0 |