Timeline for Derivation of ELBO in ADVI Paper, Jacobian of Elliptical Transformation
Current License: CC BY-SA 4.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 2, 2022 at 13:28 | history | edited | Maverick Meerkat | CC BY-SA 4.0 |
added 150 characters in body
|
| Jun 30, 2022 at 8:36 | comment | added | Steve Kroon | I think it is a bit of both: LOTUS says that we can change the parameterization of the expectation. Your argument shows that when the parameterization is changed for the Gaussian (or any location-scale) family, the resulting density for the new parameterization will be in the same family, as noted in the question: "because the Gaussian distribution is a member of the location-scale family: standardizing a Gaussian gives another Gaussian distribution." | |
| Jun 27, 2022 at 13:34 | history | answered | Maverick Meerkat | CC BY-SA 4.0 |