深度学习优化器SGD源码解析：tf/pytorch

Update rule for parameter w with gradient g when momentum is 0:

新参数 = 旧参数 - 学习率*梯度

w = w - learning_rate * g

Update rule when momentum is larger than 0:

velocity = momentum * velocity - learning_rate * g
w = w + velocity

When nesterov=True, this rule becomes:

velocity = momentum * velocity - learning_rate * g
w = w + momentum * velocity - learning_rate * g

Args
learning_rate	A Tensor, floating point value, or a schedule that is a 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.
momentum	float hyperparameter >= 0 that accelerates gradient descent in the relevant direction and dampens oscillations. Defaults to 0, i.e., vanilla gradient descent.
nesterov	boolean. Whether to apply Nesterov momentum. Defaults to False.
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 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. Every ema_overwrite_frequency steps of iterations, we overwrite the model variable by its moving average. If None, the optimizer does not overwrite model variables in the middle of training, and you need to explicitly overwrite the variables at the end of training by calling optimizer.finalize_variable_values() (which updates the model variables in-place). When using the built-in fit() 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 compilation. If no GPU device is found, this flag will be ignored.
mesh	optional tf.experimental.dtensor.Mesh instance. When provided, the optimizer will be run in DTensor mode, e.g. state tracking variable will be a DVariable, and aggregation/reduction will happen in the global DTensor context.
**kwargs	keyword arguments only used for backward compatibility.

Usage:

opt = tf.keras.optimizers.SGD(learning_rate=0.1)
var = tf.Variable(1.0)
loss = lambda: (var ** 2)/2.0         # d(loss)/d(var1) = var1
opt.minimize(loss, [var])
# Step is `- learning_rate * grad`
var.numpy()

Pytorch

 

更新参数：使用计算得到的梯度来更新模型的参数。SGD的更新规则如下：

新参数 = 旧参数 - 学习率 * 梯度

w= w - lr * g