this is for holding javascript data
Richard Guo edited subsection_Non_convex_optimization_formulation__.tex
over 8 years ago
Commit id: 678670d9c6630ff80687808d87e5cb232991a4e1
deletions | additions
diff --git a/subsection_Non_convex_optimization_formulation__.tex b/subsection_Non_convex_optimization_formulation__.tex
index ec1a9bc..595d308 100644
--- a/subsection_Non_convex_optimization_formulation__.tex
+++ b/subsection_Non_convex_optimization_formulation__.tex
...
Next, we summarize some of the key properties of this problem, which are later formalized by the paper.
\begin{enumerate}
\item When $A_0$ is orthogonal, $f(\mathbf{q}, \mathbf{Y})$ has no spurious local minima. In fact, each local minimizer $\hat{\mathbf{q}}$ corresponds to a row of $\mathbf{X}_0$ by $\hat{\mathbf{q}}^T \mathbf{Y} = \alpha \mathbf{e}_i^T \mathbf{X}_0$.
\item The feasible region $\mathbf{q} \in \mathbb{S}^{n-1}$ is a sphere with $2n$ symmetric sections, corresponding to those centered around $\pm \mathbf{e}_i$ for $i=1,\cdots,n$.
\item