0. 标量、向量、矩阵互相求导的形状
| 标量x (1,) | 向量x (n,1) | 矩阵X (n,k) | |
|
标量y (1,) |
$\frac{\partial y}{\partial x}$ (1,) | $\frac{\partial y}{\partial\textbf x}$ (1,n) | $\frac{\partial y}{\partial\textbf X}$ (k,n) |
|
向量y (m,1) |
$\frac{\partial\textbf y}{\partial x}$ (m,1) | $\frac{\partial\textbf y}{\partial\textbf x}$ (m,n) | $\frac{\partial\textbf y}{\partial\textbf X}$ (m,k,n) |
| 矩阵Y (m,l) | $\frac{\partial\textbf Y}{\partial x}$ (m,l) | $\frac{\partial\textbf Y}{\partial\textbf x}$ (m,l,n) | $\frac{\partial\textbf Y}{\partial\textbf X}$ (m,l,k,n) |
PS：默认使用列向量和分子布局（分子不变，分母转置）。
1. 标量对向量求导 $\frac{\partial y}{\partial\textbf x}$
$\textbf x\left ( n,1 \right )= \begin{bmatrix}
x_{1}\\
x_{2}\\
\vdots\\
x_{n}
\end{bmatrix}$ ，y为标量，
$\frac{\partial y}{\partial\textbf x}\left ( 1,n \right )= \begin{bmatrix}
\frac{\partial y}{\partial x_{1}} & \frac{\partial y}{\partial x_{2}} & \cdots & \frac{\partial y}{\partial x_{n}}
\end{bmatrix}$
PS：标量对列向量求导，变为行向量，标量对向量每一元素求导。
2. 向量对标量求导 $\frac{\partial\textbf y}{\partial x}$
x为标量，$\textbf y\left ( m,1 \right )= \begin{bmatrix}
y_{1}\\
y_{2}\\
\vdots\\
y_{m}
\end{bmatrix}$ ，
$\frac{\partial\textbf y}{\partial x}\left ( m,1 \right )= \begin{bmatrix}
\frac{\partial y_{1}}{\partial x}\\
\frac{\partial y_{2}}{\partial x}\\
\vdots\\
\frac{\partial y_{m}}{\partial x}
\end{bmatrix}$
PS：向量对标量求导，形状不变，向量每一元素对标量求导。
3. 向量对向量求导 $\frac{\partial\textbf y}{\partial\textbf x}$
$\textbf x\left ( n,1 \right )= \begin{bmatrix}
x_{1}\\
x_{2}\\
\vdots\\
x_{n}
\end{bmatrix}$，$\textbf y\left ( m,1 \right )= \begin{bmatrix}
y_{1}\\
y_{2}\\
\vdots\\
y_{m}
\end{bmatrix}$，
$\frac{\partial\textbf y}{\partial\textbf x}\left ( m,n \right )=
\begin{bmatrix}
\frac{\partial y_{1}}{\partial\textbf x}\\
\frac{\partial y_{2}}{\partial\textbf x}\\
\vdots\\
\frac{\partial y_{m}}{\partial\textbf x}
\end{bmatrix} =
\begin{bmatrix}
\frac{\partial y_{1}}{\partial x_{1}} & \frac{\partial y_{1}}{\partial x_{2}} & \cdots & \frac{\partial y_{1}}{\partial x_{n}}\\
\frac{\partial y_{2}}{\partial x_{1}} & \frac{\partial y_{2}}{\partial x_{2}} & \cdots & \frac{\partial y_{2}}{\partial x_{n}}\\
\vdots & \vdots & \ddots & \vdots\\
\frac{\partial y_{m}}{\partial x_{1}} & \frac{\partial y_{m}}{\partial x_{2}} & \cdots & \frac{\partial y_{m}}{\partial x_{n}}
\end{bmatrix}$
PS：向量对向量求导，形状为矩阵，可以理解为一列标量分别对向量求导。
4. 标量对矩阵求导 $\frac{\partial y}{\partial\textbf X}$
$\textbf X\left ( n,k \right )=
\begin{bmatrix}
x_{11} & x_{12} & \cdots & x_{1k}\\
x_{21} & x_{22} & \cdots & x_{2k}\\
\vdots & \vdots & \ddots & \vdots\\
x_{n1} & x_{n2} & \cdots & x_{nk}
\end{bmatrix}$，y为标量，
$\frac{\partial y}{\partial\textbf X}\left ( k,n \right )=
\begin{bmatrix}
\frac{\partial y}{\partial\textbf x_{:,1}} & \frac{\partial y}{\partial\textbf x_{:,2}} & \cdots & \frac{\partial y}{\partial\textbf x_{:,k}}
\end{bmatrix}=
\begin{bmatrix}
\frac{\partial y}{\partial x_{11}} & \frac{\partial y}{\partial x_{21}} & \cdots & \frac{\partial y}{\partial x_{n1}}\\
\frac{\partial y}{\partial x_{12}} & \frac{\partial y}{\partial x_{22}} & \cdots & \frac{\partial y}{\partial x_{n2}}\\
\vdots & \vdots & \ddots & \vdots\\
\frac{\partial y}{\partial x_{1k}} & \frac{\partial y}{\partial x_{2k}} & \cdots & \frac{\partial y}{\partial x_{nk}}
\end{bmatrix}$
PS：标量对矩阵求导，形状为转置的矩阵，可以理解为标量分别对k个列向量求导。
5. 矩阵对标量求导 $\frac{\partial\textbf Y}{\partial x}$
x为标量，$\textbf Y\left ( m,l \right )=
\begin{bmatrix}
y_{11} & y_{12} & \cdots & y_{1l}\\
y_{21} & y_{22} & \cdots & y_{2l}\\
\vdots & \vdots & \ddots & \vdots\\
y_{m1} & y_{m2} & \cdots & y_{ml}
\end{bmatrix}$，
$\frac{\partial\textbf Y}{\partial x}\left ( m,l \right )=
\begin{bmatrix}
\frac{\partial\textbf y_{:,1}}{\partial x} & \frac{\partial\textbf y_{:,2}}{\partial x} & \cdots & \frac{\partial\textbf y_{:,l}}{\partial x}
\end{bmatrix}=
\begin{bmatrix}
\frac{\partial y_{11}}{\partial x} & \frac{\partial y_{12}}{\partial x} & \cdots & \frac{\partial y_{1l}}{\partial x}\\
\frac{\partial y_{21}}{\partial x} & \frac{\partial y_{22}}{\partial x} & \cdots & \frac{\partial y_{2l}}{\partial x}\\
\vdots & \vdots & \ddots & \vdots\\
\frac{\partial y_{m1}}{\partial x} & \frac{\partial y_{m2}}{\partial x} & \cdots & \frac{\partial y_{ml}}{\partial x}
\end{bmatrix}$
PS：矩阵对标量求导，形状不变，可以理解为l个列向量分别对标量求导。
6. 向量对矩阵求导 $\frac{\partial\textbf y}{\partial\textbf X}$
$\textbf X\left ( n,k \right )=
\begin{bmatrix}
x_{11} & x_{12} & \cdots & x_{1k}\\
x_{21} & x_{22} & \cdots & x_{2k}\\
\vdots & \vdots & \ddots & \vdots\\
x_{n1} & x_{n2} & \cdots & x_{nk}
\end{bmatrix}$，$\textbf y\left ( m,1 \right )= \begin{bmatrix}
y_{1}\\
y_{2}\\
\vdots\\
y_{m}
\end{bmatrix}$，
$\frac{\partial\textbf y}{\partial\textbf X}\left ( m,k,n \right )=
\begin{bmatrix}\frac{\partial y_{1}}{\partial\textbf X}\end{bmatrix},\begin{bmatrix}\frac{\partial y_{2}}{\partial\textbf X}\end{bmatrix},\cdots,\begin{bmatrix}\frac{\partial y_{m}}{\partial\textbf X}\end{bmatrix}=\begin{bmatrix}
\frac{\partial y_{1}}{\partial x_{11}} & \frac{\partial y_{1}}{\partial x_{21}} & \cdots & \frac{\partial y_{1}}{\partial x_{n1}}\\
\frac{\partial y_{1}}{\partial x_{12}} & \frac{\partial y_{1}}{\partial x_{22}} & \cdots & \frac{\partial y_{1}}{\partial x_{n2}}\\
\vdots & \vdots & \ddots & \vdots\\
\frac{\partial y_{1}}{\partial x_{1k}} & \frac{\partial y_{1}}{\partial x_{2k}} & \cdots & \frac{\partial y_{1}}{\partial x_{nk}}
\end{bmatrix},\begin{bmatrix}
\frac{\partial y_{2}}{\partial x_{11}} & \frac{\partial y_{2}}{\partial x_{21}} & \cdots & \frac{\partial y_{2}}{\partial x_{n1}}\\
\frac{\partial y_{2}}{\partial x_{12}} & \frac{\partial y_{2}}{\partial x_{22}} & \cdots & \frac{\partial y_{2}}{\partial x_{n2}}\\
\vdots & \vdots & \ddots & \vdots\\
\frac{\partial y_{2}}{\partial x_{1k}} & \frac{\partial y_{2}}{\partial x_{2k}} & \cdots & \frac{\partial y_{2}}{\partial x_{nk}}
\end{bmatrix},\cdots,\begin{bmatrix}
\frac{\partial y_{m}}{\partial x_{11}} & \frac{\partial y_{m}}{\partial x_{21}} & \cdots & \frac{\partial y_{m}}{\partial x_{n1}}\\
\frac{\partial y_{m}}{\partial x_{12}} & \frac{\partial y_{m}}{\partial x_{22}} & \cdots & \frac{\partial y_{m}}{\partial x_{n2}}\\
\vdots & \vdots & \ddots & \vdots\\
\frac{\partial y_{m}}{\partial x_{1k}} & \frac{\partial y_{m}}{\partial x_{2k}} & \cdots & \frac{\partial y_{m}}{\partial x_{nk}}
\end{bmatrix}$
PS：向量对矩阵求导，形状为3维数组，可以理解为y的每个元素（标量）分别对矩阵求导，结果为m个k*n矩阵的组合。
7. 矩阵对向量求导 $\frac{\partial\textbf Y}{\partial\textbf x}$
$\textbf x\left ( n,1 \right )=\begin{bmatrix}
x_{1}\\
x_{2}\\
\vdots\\
x_{n}
\end{bmatrix}$，$\textbf Y\left ( m,l \right )=
\begin{bmatrix}
y_{11} & y_{12} & \cdots & y_{1l}\\
y_{21} & y_{22} & \cdots & y_{2l}\\
\vdots & \vdots & \ddots & \vdots\\
y_{m1} & y_{m2} & \cdots & y_{ml}
\end{bmatrix}$，
$\frac{\partial\textbf Y}{\partial\textbf x}\left ( m,l,n \right )=\begin{bmatrix}
\frac{\partial y_{11}}{\partial\textbf x} & \frac{\partial y_{12}}{\partial\textbf x} & \cdots & \frac{\partial y_{1l}}{\partial\textbf x}\\
\frac{\partial y_{21}}{\partial\textbf x} & \frac{\partial y_{22}}{\partial\textbf x} & \cdots & \frac{\partial y_{2l}}{\partial\textbf x}\\
\vdots & \vdots & \ddots & \vdots\\
\frac{\partial y_{m1}}{\partial\textbf x} & \frac{\partial y_{m2}}{\partial\textbf x} & \cdots & \frac{\partial y_{ml}}{\partial\textbf x}
\end{bmatrix}$
PS：矩阵对向量求导，形状为3维的数组，没搞懂，搞懂了再来写哈哈。
8. 矩阵对矩阵求导 $\frac{\partial\textbf Y}{\partial\textbf X}$
$\textbf X\left ( n,k \right )=
\begin{bmatrix}
x_{11} & x_{12} & \cdots & x_{1k}\\
x_{21} & x_{22} & \cdots & x_{2k}\\
\vdots & \vdots & \ddots & \vdots\\
x_{n1} & x_{n2} & \cdots & x_{nk}
\end{bmatrix}$，$\textbf Y\left ( m,l \right )=
\begin{bmatrix}
y_{11} & y_{12} & \cdots & y_{1l}\\
y_{21} & y_{22} & \cdots & y_{2l}\\
\vdots & \vdots & \ddots & \vdots\\
y_{m1} & y_{m2} & \cdots & y_{ml}
\end{bmatrix}$，
PS：搞懂再来写。