Type Adam
Namespace tensorflow.keras.optimizers
Parent Optimizer
Interfaces IAdam
Optimizer that implements the Adam algorithm. Adam optimization is a stochastic gradient descent method that is based on
adaptive estimation of first-order and second-order moments.
According to the paper
[Adam: A Method for Stochastic Optimization. Kingma et al.,
2014](http://arxiv.org/abs/1412.6980),
the method is "*computationally efficient, has little memory
requirement, invariant to diagonal rescaling of gradients, and is well suited
for problems that are large in terms of data/parameters*". For AMSGrad see [On The Convergence Of Adam And Beyond.
Reddi et al., 5-8](https://openreview.net/pdf?id=ryQu7f-RZ).
Methods
Properties
Public static methods
Adam NewDyn(ImplicitContainer<T> learning_rate, ImplicitContainer<T> beta_1, ImplicitContainer<T> beta_2, ImplicitContainer<T> epsilon, ImplicitContainer<T> amsgrad, ImplicitContainer<T> name, IDictionary<string, object> kwargs)
Construct a new RMSprop optimizer. Note that in the dense implementation of this algorithm, variables and their
corresponding accumulators (momentum, gradient moving average, square
gradient moving average) will be updated even if the gradient is zero
(i.e. accumulators will decay, momentum will be applied). The sparse
implementation (used when the gradient is an `IndexedSlices` object,
typically because of
tf.gather or an embedding lookup in the forward pass)
will not update variable slices or their accumulators unless those slices
were used in the forward pass (nor is there an "eventual" correction to
account for these omitted updates). This leads to more efficient updates for
large embedding lookup tables (where most of the slices are not accessed in
a particular graph execution), but differs from the published algorithm.
Parameters
-
ImplicitContainer<T>learning_rate - A Tensor or a floating point value. The learning rate.
-
ImplicitContainer<T>beta_1 -
ImplicitContainer<T>beta_2 -
ImplicitContainer<T>epsilon - Small value to avoid zero denominator.
-
ImplicitContainer<T>amsgrad -
ImplicitContainer<T>name - Optional name prefix for the operations created when applying gradients. Defaults to "RMSprop". @compatibility(eager) When eager execution is enabled, `learning_rate`, `decay`, `momentum`, and `epsilon` can each be a callable that takes no arguments and returns the actual value to use. This can be useful for changing these values across different invocations of optimizer functions. @end_compatibility
-
IDictionary<string, object>kwargs - keyword arguments. Allowed to be {`clipnorm`, `clipvalue`, `lr`, `decay`}. `clipnorm` is clip gradients by norm; `clipvalue` is clip gradients by value, `decay` is included for backward compatibility to allow time inverse decay of learning rate. `lr` is included for backward compatibility, recommended to use `learning_rate` instead.