Richard Guo edited subsection_Non_convex_optimization_formulation__.tex  over 8 years ago

Commit id: d027bffd3355f65a2d9860f43a7dd84ebc67ddf5

deletions | additions      

       

\paragraph{Symmetry and reduction}   \begin{enumerate}  \item When $\mathbf{A}_0$ is not orthogonal, it can be reduced to the orthogonal case by preconditioning $\hat{\mathbf{Y}} = \big(\frac{1}{p \theta} \mathbf{Y} \mathbf{Y}^T \big)^{-1/2} \mathbf{Y}$. \mathbf{Y}$ for some $i \in [n]$ and $\alpha \neq 0$.  \item All orthogonal $\mathbf{A}_0$ are equivalent since $f(\mathbf{q}; \mathbf{A}_0 \mathbf{X}_0) = f(\mathbf{A_0}^T \mathbf{q}; \mathbf{X}_0)$, corresponding to a rotation on $\mathbf{q}$.