# tff.learning.optimizers.build_rmsprop

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/federated/blob/v0.87.0 Version 2.0, January 2004 Licensed under the Apache License, Version 2.0 (the) |

Returns a [`tff.learning.optimizers.Optimizer`](https://www.tensorflow.org/federated/api_docs/python/tff/learning/optimizers/Optimizer) for RMSprop.

    tff.learning.optimizers.build_rmsprop(
        learning_rate: optimizer.Float,
        decay: optimizer.Float = 0.9,
        epsilon: optimizer.Float = 1e-07
    ) -> https://www.tensorflow.org/federated/api_docs/python/tff/learning/optimizers/Optimizer

The RMSprop optimizer is based on [Tieleman and Hinton, 2012](http://www.cs.toronto.edu/%7Ehinton/coursera/lecture6/lec6.pdf).

The update rule given learning rate `lr`, epsilon `eps`, decay `d`,
preconditioner `s`, weights `w` and gradients `g` is:

    s = d * s + (1 - d) * g**2
    w = w - lr * g / (sqrt(s) + eps)

<br />

<br />

<br />

| ## Args ||
|---|---|
| `learning_rate` | A positive float for learning rate, default to 0.01. |
| `decay` | A float between 0.0 and 1.0 for the decay used to track the magnitude of previous gradients. |
| `epsilon` | A small non-negative float, used to maintain numerical stability. |

<br />