Timeline for Gradient descent under the presence of symmetries
Current License: CC BY-SA 4.0
7 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Oct 3, 2023 at 13:50 | vote | accept | Asvin | ||
Oct 3, 2023 at 9:39 | answer | added | Ben McKay | timeline score: 3 | |
Oct 2, 2023 at 19:55 | comment | added | Asvin | @DanielShapero That assumption was motivated by the application in mind although perhaps the answer will turn out to be more general. | |
Oct 2, 2023 at 19:55 | history | edited | Asvin | CC BY-SA 4.0 |
edited body
|
Oct 2, 2023 at 16:05 | comment | added | Daniel Shapero | Your stipulation of finite time seems unusual and not necessary to the rest of the problem. Taking $M$ to be Euclidean space and $f(x) = |x|^2$, you only get convergence of the gradient flow $\dot x = -\nabla f$ to the minimizer $x = 0$ from an arbitrary starting point in the limit as time grows infinite. | |
Oct 2, 2023 at 14:59 | comment | added | Joseph Van Name | Shouldn't the symmetries in $G$ also preserve the Riemannian structure on $M$? | |
Oct 2, 2023 at 10:28 | history | asked | Asvin | CC BY-SA 4.0 |