更改

Where [math]A\in\mathcal{R}^{n\times n}[/math] is a full-rank n*n matrix representing the dynamics of the linear iterative system, and [math]\varepsilon_t\sim\mathcal{N}(0,\Sigma)[/math] is n-dimensional Gaussian noise with mean zero and covariance matrix [math]\Sigma[/math]. Among them, the covariance matrix [math]\Sigma[/math] is also full rank.

Where [math]A\in\mathcal{R}^{n\times n}[/math] is a full-rank n*n matrix representing the dynamics of the linear iterative system, and [math]\varepsilon_t\sim\mathcal{N}(0,\Sigma)[/math] is n-dimensional Gaussian noise with mean zero and covariance matrix [math]\Sigma[/math]. Among them, the covariance matrix [math]\Sigma[/math] is also full rank.

可以看出这一迭代系统可以看做是公式{{EquationNote|5}}的特例，其中[math]y[/math]对应这里的[math]x_{t+1}[/math]，[math]f(x_t)[/math]即是[math]A x_t[/math]。

It can be seen that this iterative system can be regarded as a special case of formula 5, where [math]y[/math] corresponds to [math]x_{t+1}[/math] here, and [math]f(x_t)[/math] is [math]A x_t[/math].

为定义EI，设干预空间大小为<math>L</math>，对于单步的映射我们可以得到维度平均有效信息

To define EI, let the intervention space size be <math>L</math>. For a single step mapping, we can obtain the average effective information of the dimensions.

 

, the EI for a single step mapping is:

<math>

<math>