5,321
edits
Unsupervised Learning: Difference between revisions
→Optimization
| Line 29: | Line 29: | ||
\end{align} | \end{align} | ||
</math> | </math> | ||
;Notes | |||
This procedure will yield us a sequence of parameters and losses.<br> | |||
<math> \mu^{0}, z^{0}, \mu^1, z^1, ...</math><br> | |||
<math> L(0) \geq L(1) \geq L(2) \geq ...</math><br> | |||
* Since the loss is monotone decreasing and bounded below, it will converge by the monotone convergence theorem. | |||
* However, this does not imply that the parameters <math>\mathbf{\mu}</math> and <math>\mathbf{z}</mathbf> will converge. | |||
====Algorithm==== | ====Algorithm==== | ||