Computes the reverse mode backpropagated gradient of the Cholesky algorithm.
tf.raw_ops.CholeskyGrad(
l, grad, name=None
)
For an explanation see "Differentiation of the Cholesky algorithm" by
Iain Murray http://arxiv.org/abs/1602.07527
Args |
l
|
A Tensor . Must be one of the following types: half , float32 , float64 .
Output of batch Cholesky algorithm l = cholesky(A). Shape is [..., M, M] .
Algorithm depends only on lower triangular part of the innermost matrices of
this tensor.
|
grad
|
A Tensor . Must have the same type as l .
df/dl where f is some scalar function. Shape is [..., M, M] .
Algorithm depends only on lower triangular part of the innermost matrices of
this tensor.
|
name
|
A name for the operation (optional).
|
Returns |
A Tensor . Has the same type as l .
|