AdagradOptimizer

class paddle.fluid.optimizer.AdagradOptimizer(learning_rate, epsilon=1e-06, regularization=None, name=None, initial_accumulator_value=0.0)[source]

The Adaptive Gradient optimizer (Adagrad for short) can adaptively assign different learning rates to individual parameters.

The parameter param_out update rule with gradient grad:

\[ \begin{align}\begin{aligned}moment\_out &= moment + grad * grad\\param\_out &= param - \frac{learning\_rate * grad}{\sqrt{moment\_out} + \epsilon}\end{aligned}\end{align} \]

Related paper: Adaptive Subgradient Methods for Online Learning and Stochastic Optimization.

The original paper does not have the epsilon attribute. It is added here in our implementation as also proposed Per-parameter adaptive learning rate methods for numerical stability to avoid the division by zero error.

Parameters
  • learning_rate (float|Variable) – The learning rate used to update Parameter. It can be a float value or a Variable with a float type.

  • epsilon (float, optional) – A small float value for numerical stability. The default value is 1e-06.

  • regularization (WeightDecayRegularizer, optional) – A Regularizer, such as L2DecayRegularizer. The default value is None.

  • name (str, optional) – Normally there is no need for user to set this property. For more information, please refer to Name. The default value is None.

  • initial_accumulator_value (float, optional) – Initial value for moment accumulator. The default value is 0.0.

Examples

import numpy as np
import paddle.fluid as fluid

np_inp = np.array([[1.0, 2.0], [3.0, 4.0]], dtype=np.float32)
inp = fluid.data(name="inp", shape=[2, 2])
out = fluid.layers.fc(inp, size=3)
out = fluid.layers.reduce_sum(out)
optimizer = fluid.optimizer.AdagradOptimizer(learning_rate=0.2)
optimizer.minimize(out)

exe = fluid.Executor(fluid.CPUPlace())
exe.run(fluid.default_startup_program())
exe.run(
    feed={"inp": np_inp},
    fetch_list=[out.name])
minimize(loss, startup_program=None, parameter_list=None, no_grad_set=None, grad_clip=None)

Add operations to minimize loss by updating parameter_list.

Parameters
  • loss (Variable) – A Variable containing the value to minimize.

  • startup_program (Program, optional) – Program for initializing parameters in parameter_list. The default value is None, at this time default_startup_program will be used.

  • parameter_list (list, optional) – List of Variable names to update to minimize loss. The default value is None, at this time all parameters will be updated.

  • no_grad_set (set, optional) – Set of Variable objects that don’t need to be updated. The default value is None.

  • grad_clip (GradClipBase, optional) – Gradient clipping strategy, static graph mode does not need to use this argument. Currently, this argument only supports gradient clipping in dygraph mode. In the future, this argument my be adjusted. The default value is None.

Returns

tuple (optimize_ops, params_grads), A list of operators appended by minimize and a list of (param, grad) variable pairs, param is Parameter, grad is the gradient value corresponding to the parameter.

Return type

tuple

Examples

Please refer to the example of current Optimizer.

set_dict(state_dict)

Load optimizer state dict. For Adam opimizer, contains beta1, beta2, momentum etc. If LearningRateDecay have been used, global_step will be changed.

Parameters

state_dict (dict) – Dict contains all the Variable needed by optimizer

Returns

None

Examples

with fluid.dygraph.guard():
    emb = fluid.dygraph.Embedding( "emb", [10, 10])

    state_dict = emb.state_dict()
    fluid.save_dygraph( state_dict, "paddle_dy")

    adam = fluid.optimizer.Adam( learning_rate = fluid.layers.noam_decay( 100, 10000) )
    state_dict = adam.state_dict()
    fluid.save_dygraph( state_dict, "padle_dy")

    para_state_dict, opti_state_dict = fluid.load_dygraph( "paddle_dy")

    adam.set_dict( opti_state_dict )
state_dict()

Get state dict information from optimizer. It contain all the variable used by optimizer. For Adam opimizer, contains beta1, beta2, momentum etc. If LearningRateDecay have been used, global_step will be include in state dict. If the optimzier never be called(minimize function), the state_dict is empty.

Args: None :returns: dict contains all the variablel used by optimizer :rtype: state_dict(dict)

Examples

import paddle.fluid as fluid
adam = fluid.optimizer.Adam(0.001)
state_dict = adam.state_dict()