TorchBicop.loglik

TorchBicop.loglik(u, x=None)

Total log-likelihood sum(log c(u)) of the pair at u.

Parameters:

uarray, shape (n, 2), dtype float

Pseudo-observations in the unit square.

xarray, shape (n, k), or None, optional

Conditioning variables forwarded to pdf().

Returns:

array, shape (), dtype float

The summed log-density (a differentiable scalar under autograd, e.g. PyTorch). The per-observation density is floored at 1e-20 before the log.