Source code for holocron.optim.radam

import torch
from . import functional as F
from torch.optim import Adam
from typing import Iterable, Tuple, Optional, Callable




class RAdam(Adam):
    """Implements the RAdam optimizer from `"On the variance of the Adaptive Learning Rate and Beyond"
    <https://arxiv.org/pdf/1908.03265.pdf>`_.

    Args:
        params (iterable): iterable of parameters to optimize or dicts defining parameter groups
        lr (float, optional): learning rate
        betas (Tuple[float, float], optional): coefficients used for running averages (default: (0.9, 0.999))
        eps (float, optional): term added to the denominator to improve numerical stability (default: 1e-8)
        weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
    """

    def __init__(
        self,
        params: Iterable[torch.nn.Parameter],
        lr: float = 1e-3,
        betas: Tuple[float, float] = (0.9, 0.999),
        eps: float = 1e-8,
        weight_decay: float = 0.
    ) -> None:
        super().__init__(params, lr, betas, eps, weight_decay, False)

    @torch.no_grad()
    def step(self, closure: Optional[Callable[[], float]] = None) -> Optional[float]:
        """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:
            params_with_grad = []
            grads = []
            exp_avgs = []
            exp_avg_sqs = []
            state_steps = []

            for p in group['params']:
                if p.grad is not None:
                    params_with_grad.append(p)
                    if p.grad.is_sparse:
                        raise RuntimeError('RAdam does not support sparse gradients.')
                    grads.append(p.grad)

                    state = self.state[p]
                    # Lazy state initialization
                    if len(state) == 0:
                        state['step'] = 0
                        # Exponential moving average of gradient values
                        state['exp_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                        # Exponential moving average of squared gradient values
                        state['exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)

                    exp_avgs.append(state['exp_avg'])
                    exp_avg_sqs.append(state['exp_avg_sq'])

                    # update the steps for each param group update
                    state['step'] += 1
                    # record the step after step update
                    state_steps.append(state['step'])

            beta1, beta2 = group['betas']
            F.radam(params_with_grad,
                    grads,
                    exp_avgs,
                    exp_avg_sqs,
                    state_steps,
                    beta1,
                    beta2,
                    group['lr'],
                    group['weight_decay'],
                    group['eps']
                    )

        return loss