mgplvm.kernels.linear module

class mgplvm.kernels.linear.Linear(n, d, scale=None, learn_scale=True, Y=None, ard=False, Poisson=False)[source]

Bases: mgplvm.kernels.kernel.Kernel

K(x, y)[source]
Parameters
xTensor

input tensor of dims (… n_samples x n x d x mx)

yTensor

input tensor of dims (… n_samples x n x d x mx)

Returns
trKTensor

trace of kernel K(x,x) with dims (… n)

Return type

Tensor

diagK(x)[source]
Return type

Tensor

property input_scale: torch.Tensor
Return type

Tensor

property msg
name = 'Linear'
property prms: Tuple[torch.Tensor, torch.Tensor]
Return type

Tuple[Tensor, Tensor]

reweight(x)[source]

re-weight the latent dimensions

Return type

Tensor

property scale: torch.Tensor
Return type

Tensor

property scale_sqr: torch.Tensor
Return type

Tensor

trK(x)[source]
Return type

Tensor

training: bool