optimizer_sgd: Stochastic gradient descent (SGD) optimizer

In SPOTMisc: Misc Extensions for the 'SPOT' Package

Stochastic gradient descent (SGD) optimizer

Description

Stochastic gradient descent optimizer with support for momentum, learning rate decay, and Nesterov momentum.

Usage

optimizer_sgd(
  learning_rate = 0.01,
  momentum = 0,
  decay = 0,
  nesterov = FALSE,
  clipnorm = NULL,
  clipvalue = NULL,
  ...
)

Arguments

learning_rate	float >= 0. Learning rate.
momentum	float >= 0. Parameter that accelerates SGD in the relevant direction and dampens oscillations.
decay	float >= 0. Learning rate decay over each update.
nesterov	boolean. Whether to apply Nesterov momentum.
clipnorm	Gradients will be clipped when their L2 norm exceeds this value.
clipvalue	Gradients will be clipped when their absolute value exceeds this value.
...	Unused, present only for backwards compatability

Details

Based on: [keras/R/optimizers.R](https://github.com/rstudio/keras/blob/main/R/optimizers.R). The following code is commented: backcompat_fix_rename_lr_to_learning_rate(...)

Value

Optimizer for use with compile.keras.engine.training.Model.

Note

To enable compatibility with the ranges of the learning rates of the other optimizers, the learning rate learning_rate is internally mapped to 10 * learning_rate. That is, a learning rat of 0.001 will be mapped to 0.01 (which is the default.)

See Also

Other optimizers: optimizer_adadelta(), optimizer_adagrad(), optimizer_adamax(), optimizer_adam(), optimizer_nadam(), optimizer_rmsprop()

SPOTMisc documentation built on Sept. 5, 2022, 5:06 p.m.