tf.keras.activations.sparsemax

Sparsemax activation function.

tf.keras.activations.sparsemax(
    x, axis=-1
)

For each batch i, and class j, sparsemax activation function is defined as:

sparsemax(x)[i, j] = max(x[i, j] - τ(x[i, :]), 0).

Args
`x`	Input tensor.
`axis`	`int`, axis along which the sparsemax operation is applied.

Returns
A tensor, output of sparsemax transformation. Has the same type and shape as `x`.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2026-10-31 UTC.

tf.keras.activations.sparsemax Stay organized with collections Save and categorize content based on your preferences.