Skip to contents

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

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


  learning_rate = 0.01,
  momentum = 0,
  nesterov = FALSE,
  weight_decay = NULL,
  clipnorm = NULL,
  clipvalue = NULL,
  global_clipnorm = NULL,
  use_ema = FALSE,
  ema_momentum = 0.99,
  ema_overwrite_frequency = NULL,
  name = "SGD",
  loss_scale_factor = NULL,
  gradient_accumulation_steps = NULL



A float, a learning_rate_schedule_* instance, or a callable that takes no arguments and returns the actual value to use. The learning rate. Defaults to 0.01.


float hyperparameter >= 0 that accelerates gradient descent in the relevant direction and dampens oscillations. 0 is vanilla gradient descent. Defaults to 0.0.


boolean. Whether to apply Nesterov momentum. Defaults to FALSE.


Float. If set, weight decay is applied.


Float. If set, the gradient of each weight is individually clipped so that its norm is no higher than this value.


Float. If set, the gradient of each weight is clipped to be no higher than this value.


Float. If set, the gradient of all weights is clipped so that their global norm is no higher than this value.


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.


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.


Int or NULL, defaults to NULL. Only used if use_ema=TRUE. Every ema_overwrite_frequency steps of iterations, we overwrite the model variable by its moving average. If NULL, 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.


String. The name to use for momentum accumulator weights created by the optimizer.


For forward/backward compatability.


Float or NULL. If a float, the scale factor will be multiplied the loss before computing gradients, and the inverse of the scale factor will be multiplied by the gradients before updating variables. Useful for preventing underflow during mixed precision training. Alternately, optimizer_loss_scale() will automatically set a loss scale factor.


Int or NULL. If an int, model & optimizer variables will not be updated at every step; instead they will be updated every gradient_accumulation_steps steps, using the average value of the gradients since the last update. This is known as "gradient accumulation". This can be useful when your batch size is very small, in order to reduce gradient noise at each update step.


an Optimizer instance