# Based on https://github.com/pytorch/pytorch/pull/3740
import torch
import math


class AdamW(torch.optim.Optimizer):
    """Implements AdamW algorithm.

    It has been proposed in `Fixing Weight Decay Regularization in Adam`_.

    Arguments:
        params (iterable): iterable of parameters to optimize or dicts defining
            parameter groups
        lr (float, optional): learning rate (default: 1e-3)
        betas (Tuple[float, float], optional): coefficients used for computing
            running averages of gradient and its square (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)

    .. Fixing Weight Decay Regularization in Adam:
    https://arxiv.org/abs/1711.05101
    """

    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
                 weight_decay=0):
        defaults = dict(lr=lr, betas=betas, eps=eps,
                        weight_decay=weight_decay)
        super(AdamW, self).__init__(params, defaults)

    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:
            loss = closure()

        for group in self.param_groups:
            for p in group['params']:
                if p.grad is None:
                    continue
                grad = p.grad.data
                if grad.is_sparse:
                    raise RuntimeError('AdamW does not support sparse gradients, please consider SparseAdam instead')

                state = self.state[p]

                # State initialization
                if len(state) == 0:
                    state['step'] = 0
                    # Exponential moving average of gradient values
                    state['exp_avg'] = torch.zeros_like(p.data)
                    # Exponential moving average of squared gradient values
                    state['exp_avg_sq'] = torch.zeros_like(p.data)

                exp_avg, exp_avg_sq = state['exp_avg'], state['exp_avg_sq']
                beta1, beta2 = group['betas']

                state['step'] += 1

                # according to the paper, this penalty should come after the bias correction
                # if group['weight_decay'] != 0:
                #     grad = grad.add(group['weight_decay'], p.data)

                # Decay the first and second moment running average coefficient
                exp_avg.mul_(beta1).add_(1 - beta1, grad)
                exp_avg_sq.mul_(beta2).addcmul_(1 - beta2, grad, grad)

                denom = exp_avg_sq.sqrt().add_(group['eps'])

                bias_correction1 = 1 - beta1 ** state['step']
                bias_correction2 = 1 - beta2 ** state['step']
                step_size = group['lr'] * math.sqrt(bias_correction2) / bias_correction1

                # w = w - wd * lr * w
                if group['weight_decay'] != 0:
                    p.data.add_(-group['weight_decay'] * group['lr'], p.data)

                # w = w - lr * w.grad
                p.data.addcdiv_(-step_size, exp_avg, denom)

                # w = w - wd * lr * w - lr * w.grad
                # See http://www.fast.ai/2018/07/02/adam-weight-decay/

        return loss