To further understand generative models it is useful to study the gradient of the cost function which is needed in order to minimize it using methods like stochastic gradient descent.
The partition function is the generating function of expectation values, in particular there are mathematical relationships between expectation values and the log-partition function. In this case we have $$ \begin{align} \langle \frac{ \partial E(\boldsymbol{x}; \theta_i) } { \partial \theta_i} \rangle_{model} = \int p(\boldsymbol{x}| \boldsymbol{\theta}) \frac{ \partial E(\boldsymbol{x}; \theta_i) } { \partial \theta_i} d\boldsymbol{x} = -\frac{\partial \log Z(\theta_i)}{ \partial \theta_i} . \tag{40} \end{align} $$
Here \( \langle \cdot \rangle_{model} \) is the expectation value over the model probability distribution \( p(\boldsymbol{x}| \boldsymbol{\theta}) \).