Adamax optimizer from Section 7 of the Adam paper. It is a variant of Adam based on the infinity norm.
optimizer_adamax(
learning_rate = 0.002,
beta_1 = 0.9,
beta_2 = 0.999,
epsilon = NULL,
decay = 0,
clipnorm = NULL,
clipvalue = NULL,
...
)float >= 0. Learning rate.
The exponential decay rate for the 1st moment estimates. float, 0 < beta < 1. Generally close to 1.
The exponential decay rate for the 2nd moment estimates. float, 0 < beta < 1. Generally close to 1.
float >= 0. Fuzz factor. If NULL, defaults to k_epsilon().
float >= 0. Learning rate decay over each update.
Gradients will be clipped when their L2 norm exceeds this value.
Gradients will be clipped when their absolute value exceeds this value.
Unused, present only for backwards compatability
Other optimizers:
optimizer_adadelta(),
optimizer_adagrad(),
optimizer_adam(),
optimizer_nadam(),
optimizer_rmsprop(),
optimizer_sgd()