SGD

class dragon.vm.torch.optim.SGD(
  params,
  lr=<object object>,
  momentum=0,
  dampening=0,
  weight_decay=0,
  nesterov=False,
  scale=1,
  clip_norm=0
)[source]

The optimizer to apply SGD algorithm.

Following SGD algorithms are supported:

VanillaSGD, whose update is defined as:

\[\text{VanillaSGD}(g) = -\text{lr} * g \]

MomentumSGD [Polyak, 1964], whose update is defined as:

\[\text{MomentumSGD}(g) = -(\text{momentum} * m_{t-1} + \text{lr} * g) \]

NesterovSGD [Sutskever et.al, 2013], whose update is defined as:

\[\text{NesterovSGD}(g) = -((1 + \text{momentum}) * m_{t} - \text{momentum} * m_{t-1}) \\ \quad \\ \text{where} \quad m_{t} = \text{momentum} * m_{t-1} + \text{lr} * g \]

You can use one of them by setting the defaults:

# Set the ``lr`` only
vanilla_sgd = torch.optim.SGD(lr=0.1)

# Set the ``lr`` and ``momentum``
momentum_sgd = torch.optim.SGD(lr=0.1, momentum=0.9)

# Set the ``lr``, ``momentum`` and ``nesterov``
nesterov_sgd = torch.optim.SGD(lr=0.1, momentum=0.9, nesterov=True)

__init__

SGD.__init__(
  params,
  lr=<object object>,
  momentum=0,
  dampening=0,
  weight_decay=0,
  nesterov=False,
  scale=1,
  clip_norm=0
)[source]

Create a SGD optimizer.

Parameters:
  • params (Sequence[dragon.vm.torch.nn.Parameter]) – The parameters to optimize.
  • lr (float, required) – The initial value to \(\text{lr}\).
  • momentum (float, optional, default=0) – The initial value to \(\text{momentum}\).
  • dampening (float, optional, default=0) – The dampening for \(\text{momentum}\).
  • weight_decay (float, optional, default=0) – The L2 penalty factor to weight.
  • nesterov (bool, optional, default=False) – True to switch to NesterovSGD optimizer.
  • scale (float, optional, default=1) – The scaling factor to gradient.
  • clip_norm (float, optional, default=0) – The maximum L2 norm to clip gradient.

Methods

add_param_group

Optimizer.add_param_group(param_group)[source]

Add a new param group into the optimizer.

attr:param_group is a dict containing the defaults:

# A group defined ``lr`` and ``weight_decay``
param_group = {'params': [], 'lr': 0.01, 'weight_decay': 0.0001}
Parameters:
  • param_group (dict) – The param group to add.

step

Optimizer.step()[source]

Update all parameter groups using gradients.

Call this method after a backward pass:

x = torch.ones(1, 3, requires_grad=True)
y = x + 1
y.backward()
optimizer.step()

sum_grad

Optimizer.sum_grad()[source]

Sum the gradients of all parameters.

Call this method after each backward pass:

x = torch.ones(1, requires_grad=True)
optimizer = torch.optim.SGD([x], lr=0.1)
for epoch in range(2):
    for step in range(3):
        y = x + 1
        y.backward()
        optimizer.sum_grad()
    optimizer.step()
print(x)  # 0.4

zero_grad

Optimizer.zero_grad(set_to_none=False)[source]

Set the gradients of all parameters to zero.

This method is not necessary usually, as we will overwrite the gradients in the next computation.

However, if some gradients are not computed every time, remember to set them to none before step(...):

m1 = torch.nn.Linear(3, 3)
m2 = torch.nn.Linear(3, 3)
x = torch.ones(1, 3, requires_grad=True)
for i in range(10):
    x = m1(x)
    if i in (2, 4, 6):
        x += m2(x)
optimizer.zero_grad(set_to_none=True)
x.backward()
optimizer.step()
Parameters:
  • set_to_none (bool, optional, default=False) – Whether to remove the gradients instead of zeroing.