{ }
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
Returns | |
---|---|
A Tensor . Has the same type as l .
|