Caffe2 - Python API
A deep learning, cross platform ML framework
Public Member Functions | List of all members
torch.optim.adagrad.Adagrad Class Reference
Inheritance diagram for torch.optim.adagrad.Adagrad:

Public Member Functions

def __init__ (self, params, lr=1e-2, lr_decay=0, weight_decay=0, initial_accumulator_value=0)
def share_memory (self)
def step (self, closure=None)

Detailed Description

Implements Adagrad algorithm.

It has been proposed in `Adaptive Subgradient Methods for Online Learning
and Stochastic Optimization`_.

    params (iterable): iterable of parameters to optimize or dicts defining
        parameter groups
    lr (float, optional): learning rate (default: 1e-2)
    lr_decay (float, optional): learning rate decay (default: 0)
    weight_decay (float, optional): weight decay (L2 penalty) (default: 0)

.. _Adaptive Subgradient Methods for Online Learning and Stochastic

Definition at line 5 of file

Member Function Documentation

def torch.optim.adagrad.Adagrad.step (   self,
  closure = None 
Performs a single optimization step.

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

Definition at line 48 of file

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