Timeline for VAEs - Two questions regarding the posterior and prior distribution derivations
Current License: CC BY-SA 4.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 16 at 13:30 | comment | added | Firebug | @DrPrItay Categorically no, you can have whatever distributions you want for approximate posterior and prior. It's just that Gaussian leads to closed-form expressions, but it didn't have to be the case | |
| Oct 16 at 11:45 | comment | added | DrPrItay | Thank you! Regarding my 2nd question: im not sure about the following. I understand that the posterior is our choice and doesnt have to be a gaussian, my question is, given that the posterior is chosen to be a gaussiam, does it necessitate mathematically that the prior is also a gaussian? It doesnt make sense to me if it does, but it seems as if in the paper they treat it as this is the case (or my understanding is poor) | |
| Oct 16 at 11:00 | history | answered | Firebug | CC BY-SA 4.0 |