Adamax
class
tf.keras.optimizers.Adamax( learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-07, weight_decay=None, clipnorm=None, clipvalue=None, global_clipnorm=None, use_ema=False, ema_momentum=0.99, ema_overwrite_frequency=None, jit_compile=True, name="Adamax", **kwargs)
Optimizer that implements the Adamax algorithm.
Adamax, a variant of Adam based on the infinity norm, is a first-ordergradient-based optimization method. Due to its capability of adjusting thelearning rate based on data characteristics, it is suited to learntime-variant process, e.g., speech data with dynamically changed noiseconditions. Default parameters follow those provided in the paper (seereferences below).
Initialization:
m = 0 # Initialize initial 1st moment vectoru = 0 # Initialize the exponentially weighted infinity normt = 0 # Initialize timestep
The update rule for parameter w
with gradient g
is described at the endof section 7.1 of the paper (see the referenece section):
t += 1m = beta1 * m + (1 - beta) * gu = max(beta2 * u, abs(g))current_lr = learning_rate / (1 - beta1 ** t)w = w - current_lr * m / (u + epsilon)
Arguments
- learning_rate: A
tf.Tensor
, floating point value, a schedule that is atf.keras.optimizers.schedules.LearningRateSchedule
, or a callable that takes no arguments and returns the actual value to use. The learning rate. Defaults to 0.001. - beta_1: A float value or a constant float tensor. The exponential decay rate for the 1st moment estimates.
- beta_2: A float value or a constant float tensor. The exponential decay rate for the exponentially weighted infinity norm.
- epsilon: A small constant for numerical stability.
- name: String. The name to use for momentum accumulator weights created by the optimizer.
- weight_decay: Float, defaults to None. If set, weight decay is applied.
- clipnorm: Float. If set, the gradient of each weight is individually clipped so that its norm is no higher than this value.
- clipvalue: Float. If set, the gradient of each weight is clipped to be no higher than this value.
- global_clipnorm: Float. If set, the gradient of all weights is clipped so that their global norm is no higher than this value.
- use_ema: Boolean, defaults to False. If True, exponential moving average (EMA) is applied. EMA consists of computing an exponential moving average of the weights of the model (as the weight values change after each training batch), and periodically overwriting the weights with their moving average.
- ema_momentum: Float, defaults to 0.99. Only used if
use_ema=True
. This is # noqa: E501 the momentum to use when computing the EMA of the model's weights:new_average = ema_momentum * old_average + (1 - ema_momentum) * current_variable_value
. - ema_overwrite_frequency: Int or None, defaults to None. Only used if
use_ema=True
. Everyema_overwrite_frequency
steps of iterations, we overwrite the model variable by its moving average. If None, the optimizer # noqa: E501 does not overwrite model variables in the middle of training, and you need to explicitly overwrite the variables at the end of training by callingoptimizer.finalize_variable_values()
(which updates the model # noqa: E501 variables in-place). When using the built-infit()
training loop, this happens automatically after the last epoch, and you don't need to do anything. - jit_compile: Boolean, defaults to True. If True, the optimizer will use XLA # noqa: E501 compilation. If no GPU device is found, this flag will be ignored.
- **kwargs: keyword arguments only used for backward compatibility.
Reference