tff.learning.optimizers.build_rmsprop
Returns a 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
) -> tff.learning.optimizers.Optimizer
The RMSprop optimizer is based on Tieleman and Hinton, 2012.
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)
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.
|
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.
Last updated 2024-09-20 UTC.
[null,null,["Last updated 2024-09-20 UTC."],[],[]]