fix http://disq.us/p/25bssra

Gabyjojo · Nov 3, 2019 · bc87393 · bc87393
1 parent 8612f8b
commit bc87393
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/docs/03-Linear-Methods-for-Regression/3.4-Shrinkage-Methods.md b/docs/03-Linear-Methods-for-Regression/3.4-Shrinkage-Methods.md
@@ -126,7 +126,7 @@ $$
 > $$
 > 式中
 > $$
-> S=U^TV
+> S=U^TAV
 > $$
 > 若选择$U$和$V$为正交矩阵，则他们的选择各存在$n^2-n$个自由度．他提出利用这些自由度使矩阵$S$的非对角元为0，即矩阵$S=\Sigma=diag(\sigma_1,\sigma_2,\ldots,\sigma_n)$为对角矩阵．则
 > $$