Deep Learning: Difference between revisions
| Line 1,265: | Line 1,265: | ||
Lemma: If linearly stable but <math>\rho(J(\theta^*)) < 1</math> then asymptotic stability. | Lemma: If linearly stable but <math>\rho(J(\theta^*)) < 1</math> then asymptotic stability. | ||
;Def Strongly local min-max | |||
<math> | |||
\begin{cases} | |||
\lambda_{min}(\nabla^2_{xx} f) > 0\\ | |||
\lambda_{max}(\nabla^2_{yy} f) < 0 | |||
\end{cases} | |||
</math> | |||
==Misc== | ==Misc== | ||