torch (version 0.8.1)

optim_sgd: SGD optimizer

Description

Implements stochastic gradient descent (optionally with momentum). Nesterov momentum is based on the formula from On the importance of initialization and momentum in deep learning.

Usage

optim_sgd(
  params,
  lr = optim_required(),
  momentum = 0,
  dampening = 0,
  weight_decay = 0,
  nesterov = FALSE
)

Arguments

params

(iterable): iterable of parameters to optimize or dicts defining parameter groups

lr

(float): learning rate

momentum

(float, optional): momentum factor (default: 0)

dampening

(float, optional): dampening for momentum (default: 0)

weight_decay

(float, optional): weight decay (L2 penalty) (default: 0)

nesterov

(bool, optional): enables Nesterov momentum (default: FALSE)

Warning

If you need to move a model to GPU via $cuda(), please do so before constructing optimizers for it. Parameters of a model after $cuda() will be different objects from those before the call. In general, you should make sure that the objects pointed to by model parameters subject to optimization remain the same over the whole lifecycle of optimizer creation and usage.

Examples

if (torch_is_installed()) {
if (FALSE) {
optimizer <- optim_sgd(model$parameters(), lr = 0.1, momentum = 0.9)
optimizer$zero_grad()
loss_fn(model(input), target)$backward()
optimizer$step()
}

}