TorchVinecop.from_vinecop

classmethod TorchVinecop.from_vinecop(cop, cache_integrals=True, device=None, dtype=torch.float64)

Lifts a fitted Vinecop into a TorchVinecop.

Each pair copula is lifted via from_bicop(), so the resulting cascade matches the Vinecop evaluator to within bilinear-interpolation precision on the shared grid.

Parameters:
copVinecop

A fitted Vinecop whose pair copulas are all TLL or independence families. Discrete variables are not supported.

cache_integralsbool, default=True

Forwarded to from_bicop() for every pair copula.

devicetorch.device or None, default=None

Placement of the underlying tensors.

dtypetorch.dtype, default=torch.float64

Precision of the underlying tensors.

Returns:
TorchVinecop

A TorchVinecop mirroring cop.