<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/vi/csiszar_divergence.py#L737-L778) |

The Modified-GAN Csiszar-function in log-space.

    tfp.vi.modified_gan(
        logu, self_normalized=False, name=None
    )

A Csiszar-function is a member of,

    F = { f:R_+ to R : f convex }.

When `self_normalized = True` the modified-GAN (Generative/Adversarial
Network) Csiszar-function is:

    f(u) = log(1 + u) - log(u) + 0.5 (u - 1)

When `self_normalized = False` the `0.5 (u - 1)` is omitted.

The unmodified GAN Csiszar-function is identical to Jensen-Shannon (with
`self_normalized = False`).

> [!WARNING]
> **Warning:** this function makes non-log-space calculations and may therefore be numerically unstable for `|logu| >> 0`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `logu` | `float`-like `Tensor` representing `log(u)` from above. |
| `self_normalized` | Python `bool` indicating whether `f'(u=1)=0`. When `f'(u=1)=0` the implied Csiszar f-Divergence remains non-negative even when `p, q` are unnormalized measures. |
| `name` | Python `str` name prefixed to Ops created by this function. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| `chi_square_of_u` | `float`-like `Tensor` of the Csiszar-function evaluated at `u = exp(logu)`. |

<br />