Timeline for How do local minima occur in the equation of loss function?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 29, 2020 at 10:26 | comment | added | Dave | The idea that the gradient is zero only for the perfect fit is incorrect. | |
| Jul 29, 2020 at 10:25 | history | edited | Dave | CC BY-SA 4.0 | added 67 characters in body |
| Jul 29, 2020 at 5:55 | comment | added | Itamar Mushkin | Yes, of course it has a minimum - but it's a global minimum. OP asked about local minima other than the global minimum. | |
| Jul 28, 2020 at 22:31 | comment | added | Dave | The critical point is $(\hat{\beta}_0, \hat{beta}_1) = (\frac{8}{7}, \frac{9}{14})$. The eigenvalues of the Hessian matrix at $(\frac{8}{7}, \frac{9}{14})$ are $13\pm\sqrt{113}$, both of which are $>0$, making the critical point a minimum. | |
| Jul 28, 2020 at 18:14 | comment | added | Itamar Mushkin | This loss function does not have any local minima though... | |
| Jul 28, 2020 at 14:20 | history | answered | Dave | CC BY-SA 4.0 |