mindspore.nn.FTRL

class mindspore.nn.FTRL(params, initial_accum=0.1, learning_rate=0.001, lr_power=- 0.5, l1=0.0, l2=0.0, use_locking=False, loss_scale=1.0, weight_decay=0.0)[source]

Implements the FTRL algorithm.

FTRL is an online convex optimization algorithm that adaptively chooses its regularization function based on the loss functions. Refer to paper Adaptive Bound Optimization for Online Convex Optimization.

The updating formulas are as follows,

\[\begin{split}\begin{array}{ll} \\ m_{t+1} = m_{t} + g^2 \\ u_{t+1} = u_{t} + g - \frac{m_{t+1}^\text{-p} - m_{t}^\text{-p}}{\alpha } * \omega_{t} \\ \omega_{t+1} = \begin{cases} \frac{(sign(u_{t+1}) * l1 - u_{t+1})}{\frac{m_{t+1}^\text{-p}}{\alpha } + 2 * l2 } & \text{ if } |u_{t+1}| > l1 \\ 0.0 & \text{ otherwise } \end{cases}\\ \end{array}\end{split}\]

\(m\) represents accumulators, \(g\) represents grads, \(t\) represents the current step, \(u\) represents the linear coefficient to be updated, \(p\) represents lr_power, \(\alpha\) represents learning_rate, \(\omega\) represents params.

Note

The sparse strategy is applied while the SparseGatherV2 operator is used for forward network. If the sparse strategy wants to be executed on the host, set the target to the CPU. The sparse feature is under continuous development.

If parameters are not grouped, the weight_decay in optimizer will be applied on the network parameters without ‘beta’ or ‘gamma’ in their names. Users can group parameters to change the strategy of decaying weight. When parameters are grouped, each group can set weight_decay. If not, the weight_decay in optimizer will be applied.

Parameters

  • params (Union[list[Parameter], list[dict]]) –

    Must be list of Parameter or list of dict. When the params is a list of dict, the string “params”, “weight_decay”, “grad_centralization” and “order_params” are the keys can be parsed.

    • params: Required. Parameters in current group. The value must be a list of Parameter.

    • lr: Using different learning rate by grouping parameters is currently not supported.

    • weight_decay: Optional. If “weight_decay” in the keys, the value of corresponding weight decay will be used. If not, the weight_decay in the optimizer will be used. It should be noted that weight decay can be a constant value or a Cell. It is a Cell only when dynamic weight decay is applied. Dynamic weight decay is similar to dynamic learning rate, users need to customize a weight decay schedule only with global step as input, and during training, the optimizer calls the instance of WeightDecaySchedule to get the weight decay value of current step.

    • grad_centralization: Optional. Must be Boolean. If “grad_centralization” is in the keys, the set value will be used. If not, the grad_centralization is False by default. This configuration only works on the convolution layer.

    • order_params: Optional. When parameters is grouped, this usually is used to maintain the order of parameters that appeared in the network to improve performance. The value should be parameters whose order will be followed in optimizer. If order_params in the keys, other keys will be ignored and the element of ‘order_params’ must be in one group of params.

  • initial_accum (float) – The starting value for accumulators m, must be zero or positive values. Default: 0.1 .

  • learning_rate (float) – The learning rate value, must be zero or positive, dynamic learning rate is currently not supported. Default: 0.001 .

  • lr_power (float) – Learning rate power controls how the learning rate decreases during training, must be less than or equal to zero. Use fixed learning rate if lr_power is zero. Default: -0.5 .

  • l1 (float) – l1 regularization strength, must be greater than or equal to zero. Default: 0.0 .

  • l2 (float) – l2 regularization strength, must be greater than or equal to zero. Default: 0.0 .

  • use_locking (bool) – If true, use locks for updating operation. Default: False .

  • loss_scale (float) – Value for the loss scale. It must be greater than 0.0. In general, use the default value. Only when FixedLossScaleManager is used for training and the drop_overflow_update in FixedLossScaleManager is set to False , then this value needs to be the same as the loss_scale in FixedLossScaleManager. Refer to class mindspore.amp.FixedLossScaleManager for more details. Default: 1.0 .

  • weight_decay (Union[float, int, Cell]) –

    Weight decay (L2 penalty). Default: 0.0 .

    • float: The fixed weight decay value. Must be equal to or greater than 0.

    • int: The fixed weight decay value. Must be equal to or greater than 0. It will be converted to float.

    • Cell: Weight decay is dynamic. During training, the optimizer calls the instance of the Cell with step as the input to get the weight decay value of current step.

Inputs:

  • grads (tuple[Tensor]) - The gradients of params in the optimizer, the shape is the same as the params in optimizer.

Outputs:

Tuple[Parameter], the updated parameters, the shape is the same as params.

Raises

  • TypeError – If initial_accum, learning_rate, lr_power, l1, l2 or loss_scale is not a float.

  • TypeError – If element of parameters is neither Parameter nor dict.

  • TypeError – If weight_decay is neither float nor int.

  • TypeError – If use_nesterov is not a bool.

  • ValueError – If lr_power is greater than 0.

  • ValueError – If loss_scale is less than or equal to 0.

  • ValueError – If initial_accum, l1 or l2 is less than 0.

Supported Platforms:

Ascend GPU

Examples

>>> import mindspore as ms
>>> from mindspore import nn
>>>
>>> # Define the network structure of LeNet5. Refer to
>>> # https://gitee.com/mindspore/docs/blob/r2.1/docs/mindspore/code/lenet.py
>>> net = LeNet5()
>>> #1) All parameters use the same learning rate and weight decay
>>> optim = nn.FTRL(params=net.trainable_params())
>>>
>>> #2) Use parameter groups and set different values
>>> conv_params = list(filter(lambda x: 'conv' in x.name, net.trainable_params()))
>>> no_conv_params = list(filter(lambda x: 'conv' not in x.name, net.trainable_params()))
>>> group_params = [{'params': conv_params, 'weight_decay': 0.01, 'grad_centralization':True},
...                 {'params': no_conv_params},
...                 {'order_params': net.trainable_params()}]
>>> optim = nn.FTRL(group_params, learning_rate=0.1, weight_decay=0.0)
>>> # The conv_params's parameters will use default learning rate of 0.1 and weight decay of 0.01 and grad
>>> # centralization of True.
>>> # The no_conv_params's parameters will use default learning rate of 0.1 will use default weight decay
>>> # of 0.0 and grad centralization of False.
>>> # The final parameters order in which the optimizer will be followed is the value of 'order_params'.
>>>
>>> loss = nn.SoftmaxCrossEntropyWithLogits()
>>> model = ms.train.Model(net, loss_fn=loss, optimizer=optim)