merlin.models.tf.LazyAdam

class merlin.models.tf.LazyAdam(learning_rate: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64, Callable] = 0.001, beta_1: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64] = 0.9, beta_2: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64] = 0.999, epsilon: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64] = 1e-07, amsgrad: bool = False, name: str = 'LazyAdam', **kwargs)

Bases: keras.optimizers.legacy.adam.Adam

Variant of the Adam optimizer that handles sparse updates more efficiently.

The original Adam algorithm maintains two moving-average accumulators for each trainable variable; the accumulators are updated at every step. This class provides lazier handling of gradient updates for sparse variables. It only updates moving-average accumulators for sparse variable indices that appear in the current batch, rather than updating the accumulators for all indices. Compared with the original Adam optimizer, it can provide large improvements in model training throughput for some applications. However, it provides slightly different semantics than the original Adam algorithm, and may lead to different empirical results.

Note, amsgrad is currently not supported and the argument can only be False.

This implementation was adapted from the original Tensforflow Addons implementation of TensorFlow Addons Optimizers: LazyAdam: tensorflow/addons

__init__(learning_rate: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64, Callable] = 0.001, beta_1: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64] = 0.9, beta_2: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64] = 0.999, epsilon: Union[tensorflow.python.framework.ops.Tensor, float, numpy.float16, numpy.float32, numpy.float64] = 1e-07, amsgrad: bool = False, name: str = 'LazyAdam', **kwargs)

Constructs a new LazyAdam optimizer.

Parameters

• learning_rate (Union[FloatTensorLike, Callable]) – A Tensor or a floating point value. or a schedule that is a tf.keras.optimizers.legacy.schedules.LearningRateSchedule The learning rate. FloatTensorLike = Union[tf.Tensor, float, np.float16, np.float32, np.float64]

• beta_1 (FloatTensorLike) – A float value or a constant float tensor. The exponential decay rate for the 1st moment estimates.

• beta_2 (FloatTensorLike) – A float value or a constant float tensor. The exponential decay rate for the 2nd moment estimates.

• epsilon (FloatTensorLike) – A small constant for numerical stability. This epsilon is “epsilon hat” in [Adam: A Method for Stochastic Optimization. Kingma et al., 2014](http://arxiv.org/abs/1412.6980) (in the formula just before Section 2.1), not the epsilon in Algorithm 1 of the paper.

• amsgrad (bool) – Whether to apply AMSGrad variant of this algorithm from the paper “On the Convergence of Adam and beyond”. Note that this argument is currently not supported and the argument can only be False.

• name (str) – Optional name for the operations created when applying gradients. Defaults to “LazyAdam”.

• **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.

Methods

__init__([learning_rate, beta_1, beta_2, ...])	Constructs a new LazyAdam optimizer.
add_slot(var, slot_name[, initializer, shape])	Add a new slot variable for var.
add_weight(name, shape[, dtype, ...])
apply_gradients(grads_and_vars[, name, ...])	Apply gradients to variables.
from_config(config[, custom_objects])	Creates an optimizer from its config.
get_config()
get_gradients(loss, params)	Returns gradients of loss with respect to params.
get_slot(var, slot_name)
get_slot_names()	A list of names for this optimizer's slots.
get_updates(loss, params)
get_weights()
minimize(loss, var_list[, grad_loss, name, tape])	Minimize loss by updating var_list.
set_weights(weights)
variables()	Returns variables of this Optimizer based on the order created.

Attributes

clipnorm	float or None.
clipvalue	float or None.
global_clipnorm	float or None.
iterations	Variable.
weights	Returns variables of this Optimizer based on the order created.

get_weights()