torch_pinverse(self, rcond = 0)



(Tensor) The input tensor of size \((*, m, n)\) where \(*\) is zero or more batch dimensions


(float) A floating point value to determine the cutoff for small singular values. Default: 1e-15


This method is implemented using the Singular Value Decomposition.
The pseudo-inverse is not necessarily a continuous function in the elements of the matrix `[1]`_.
Therefore, derivatives are not always existent, and exist for a constant rank only `[2]`_.
However, this method is backprop-able due to the implementation by using SVD results, and
could be unstable. Double-backward will also be unstable due to the usage of SVD internally.
See `~torch.svd` for more details.

pinverse(input, rcond=1e-15) -> Tensor

Calculates the pseudo-inverse (also known as the Moore-Penrose inverse) of a 2D tensor. Please look at Moore-Penrose inverse_ for more details


if (torch_is_installed()) { input = torch_randn(c(3, 5)) input torch_pinverse(input) # Batched pinverse example a = torch_randn(c(2,6,3)) b = torch_pinverse(a) torch_matmul(b, a) }
#> torch_tensor #> (1,.,.) = #> 1.0000e+00 -7.4506e-09 1.8626e-09 #> -1.1176e-08 1.0000e+00 -1.3039e-08 #> -1.6391e-07 1.4901e-08 1.0000e+00 #> #> (2,.,.) = #> 1.0000e+00 4.1723e-07 -1.7881e-07 #> -1.7881e-07 1.0000e+00 -1.4901e-07 #> 2.0862e-07 -2.0117e-07 1.0000e+00 #> [ CPUFloatType{2,3,3} ]