<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/ops/linalg.py#L65-L84) |

Computes the inverse of a symmetric positive-definite matrix.

#### View aliases


**Main aliases**

[`tf.keras.ops.linalg.cholesky_inverse`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/cholesky_inverse)

<br />

    tf.keras.ops.cholesky_inverse(
        x, upper=False
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `x` | Input tensor of shape `(..., M, M)`. |
| `upper` | `bool` <br /> Determines whether to use the upper- or lower-triangular factor for the internal computation. Defaults to False. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A tensor of shape `(..., M, M)` representing the inverse of `x`. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | If `x` is not a symmetric positive-definite matrix. |

<br />