e4bdbe76308dbeff50741415ab8c080ef99a7d70,pymc3/distributions/multivariate.py,LKJCholeskyCov,logp,#LKJCholeskyCov#Any#,698

Before Change

        // Compute the log det jacobian of the second transformation
        // described in the docstring.
        count = np.arange(self.n - 1)
        det_invjac = - (count * tt.log(sd_vals[1:])).sum()
        det_invjac += - tt.log(x[diag_idxs]).sum() + tt.log(x[0])

        norm = _lkj_normalizing_constant(eta, self.n)

After Change

        variance = tt.inc_subtensor(
            variance[1:],
            cumsum[diag_idxs[1:]] - cumsum[diag_idxs[:-1]])
        sd_vals = tt.sqrt(variance)

        logp_sd = self.sd_dist.logp(sd_vals).sum()
        corr_diag = x[diag_idxs] / sd_vals

        logp_lkj = (2 * eta - 3 + n - tt.arange(n)) * np.log(corr_diag)
        logp_lkj = tt.sum(logp_lkj)

        // Compute the log det jacobian of the second transformation
        // described in the docstring.
        idx = tt.arange(n)

Instances