Source code for torch.optim.adadelta

import torch

from .optimizer import Optimizer

[docs]class Adadelta(Optimizer): """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) __ """ def __init__(self, params, lr=1.0, rho=0.9, eps=1e-6, weight_decay=0): if not 0.0 <= lr: raise ValueError("Invalid learning rate: {}".format(lr)) if not 0.0 <= rho <= 1.0: raise ValueError("Invalid rho value: {}".format(rho)) if not 0.0 <= eps: raise ValueError("Invalid epsilon value: {}".format(eps)) if not 0.0 <= weight_decay: raise ValueError("Invalid weight_decay value: {}".format(weight_decay)) defaults = dict(lr=lr, rho=rho, eps=eps, weight_decay=weight_decay) super(Adadelta, self).__init__(params, defaults)
[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('Adadelta 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) state['acc_delta'] = torch.zeros_like(p, memory_format=torch.preserve_format) square_avg, acc_delta = state['square_avg'], state['acc_delta'] rho, eps = group['rho'], group['eps'] state['step'] += 1 if group['weight_decay'] != 0: grad = grad.add(p, alpha=group['weight_decay']) square_avg.mul_(rho).addcmul_(grad, grad, value=1 - rho) std = square_avg.add(eps).sqrt_() delta = acc_delta.add(eps).sqrt_().div_(std).mul_(grad) p.add_(delta, alpha=-group['lr']) acc_delta.mul_(rho).addcmul_(delta, delta, value=1 - rho) 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