tf.keras.ops.matrix_power

Note: This API is new and only available via pip install tf-nightly.

Raise a square matrix to the (integer) power n.

View aliases

Main aliases

tf.keras.ops.linalg.matrix_power

tf.keras.ops.matrix_power(
    x, n
)

For positive integers n, the power is computed by repeated matrix squarings and matrix multiplications. If n == 0, the identity matrix of the same shape as x is returned. If n < 0, the inverse is computed and then raised to the abs(n).

Args
x	Input tensor of shape (..., M, M).
n	Exponent (integer).

Returns
A tensor of shape (..., M, M) representing x**n.

Example:

x = keras.ops.convert_to_tensor([[1., 2.], [3., 4.]])
matrix_power(x, 3)
array([[ 37.,  54.],
       [ 81., 118.]], dtype=float32)