torch.optim.adadelta.Adadelta Class Reference

Inheritance diagram for torch.optim.adadelta.Adadelta:

Public Member Functions
def	__init__ (self, params, lr=1.0, rho=0.9, eps=1e-6, weight_decay=0)
def	step (self, closure=None)

Detailed Description

Implements Adadelta algorithm.

It has been proposed in `ADADELTA: An Adaptive Learning Rate Method`__.

Arguments:
    params (iterable): iterable of parameters to optimize or dicts defining
        parameter groups
    rho (float, optional): coefficient used for computing a running average
        of squared gradients (default: 0.9)
    eps (float, optional): term added to the denominator to improve
        numerical stability (default: 1e-6)
    lr (float, optional): coefficient that scale delta before it is applied
        to the parameters (default: 1.0)
    weight_decay (float, optional): weight decay (L2 penalty) (default: 0)

__ https://arxiv.org/abs/1212.5701

Definition at line 6 of file adadelta.py.

Member Function Documentation

def torch.optim.adadelta.Adadelta.step	(		self,
			closure = None
	)

Performs a single optimization step.

Arguments:
    closure (callable, optional): A closure that reevaluates the model
and returns the loss.

Definition at line 38 of file adadelta.py.

---

The documentation for this class was generated from the following file:

• torch/optim/adadelta.py