bayespy.utils.random.gamma_logpdf¶

bayespy.utils.random.gamma_logpdf(bx, logx, a_logx, a_logb, gammaln_a)[source]¶

Log-density of $\mathcal{G}(x|a,b)$ .

If you want to get the gradient, just let each parameter be a gradient of that term.

Parameters:

bx (ndarray) – $bx$
logx (ndarray) – $\log(x)$
a_logx (ndarray) – $a \log(x)$
a_logb (ndarray) – $a \log(b)$
gammaln_a (ndarray) – $\log\Gamma(a)$