Source code for torch.optim.rmsprop

import torch
from .optimizer import Optimizer

[docs]class RMSprop(Optimizer): r"""Implements RMSprop algorithm. Proposed by G. Hinton in his `course <>`_. The centered version first appears in `Generating Sequences With Recurrent Neural Networks <>`_. The implementation here takes the square root of the gradient average before adding epsilon (note that TensorFlow interchanges these two operations). The effective learning rate is thus :math:`\alpha/(\sqrt{v} + \epsilon)` where :math:`\alpha` is the scheduled learning rate and :math:`v` is the weighted moving average of the squared gradient. Arguments: params (iterable): iterable of parameters to optimize or dicts defining parameter groups lr (float, optional): learning rate (default: 1e-2) momentum (float, optional): momentum factor (default: 0) alpha (float, optional): smoothing constant (default: 0.99) eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-8) centered (bool, optional) : if ``True``, compute the centered RMSProp, the gradient is normalized by an estimation of its variance weight_decay (float, optional): weight decay (L2 penalty) (default: 0) """ def __init__(self, params, lr=1e-2, alpha=0.99, eps=1e-8, weight_decay=0, momentum=0, centered=False): if not 0.0 <= lr: raise ValueError("Invalid learning rate: {}".format(lr)) if not 0.0 <= eps: raise ValueError("Invalid epsilon value: {}".format(eps)) if not 0.0 <= momentum: raise ValueError("Invalid momentum value: {}".format(momentum)) if not 0.0 <= weight_decay: raise ValueError("Invalid weight_decay value: {}".format(weight_decay)) if not 0.0 <= alpha: raise ValueError("Invalid alpha value: {}".format(alpha)) defaults = dict(lr=lr, momentum=momentum, alpha=alpha, eps=eps, centered=centered, weight_decay=weight_decay) super(RMSprop, self).__init__(params, defaults) def __setstate__(self, state): super(RMSprop, self).__setstate__(state) for group in self.param_groups: group.setdefault('momentum', 0) group.setdefault('centered', False)
[docs] @torch.no_grad() def step(self, closure=None): """Performs a single optimization step. Arguments: closure (callable, optional): A closure that reevaluates the model and returns the loss. """ loss = None if closure is not None: with torch.enable_grad(): loss = closure() for group in self.param_groups: for p in group['params']: if p.grad is None: continue grad = p.grad if grad.is_sparse: raise RuntimeError('RMSprop does not support sparse gradients') state = self.state[p] # State initialization if len(state) == 0: state['step'] = 0 state['square_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format) if group['momentum'] > 0: state['momentum_buffer'] = torch.zeros_like(p, memory_format=torch.preserve_format) if group['centered']: state['grad_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format) square_avg = state['square_avg'] alpha = group['alpha'] state['step'] += 1 if group['weight_decay'] != 0: grad = grad.add(p, alpha=group['weight_decay']) square_avg.mul_(alpha).addcmul_(grad, grad, value=1 - alpha) if group['centered']: grad_avg = state['grad_avg'] grad_avg.mul_(alpha).add_(grad, alpha=1 - alpha) avg = square_avg.addcmul(grad_avg, grad_avg, value=-1).sqrt_().add_(group['eps']) else: avg = square_avg.sqrt().add_(group['eps']) if group['momentum'] > 0: buf = state['momentum_buffer'] buf.mul_(group['momentum']).addcdiv_(grad, avg) p.add_(buf, alpha=-group['lr']) else: p.addcdiv_(grad, avg, value=-group['lr']) return loss


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources