pytorch 正则化公式推导+实现+Adam优化器源码以及weight decay的设置

推荐阅读：pytorch实现L2和L1正则化regularization的方法

预备知识：深度学习的优化器（各类 optimizer 的原理、优缺点及数学推导）

1.为什么要进行正则化？怎么正则化？

pytorch —— 正则化之weight_decay
上文简述：

误差可分解为偏差，方差与噪声之和，即 误差=偏差+方差+噪声 之和；

偏差度量了学习算法的期望预测与真实结果的偏离程度，即刻画了学习算法本身的拟合能力；

方差度量了同样大小的训练集的变动所导致的学习性能的变化，即刻画了数据扰动所造成的影响；

噪声则表达了在当前任务上任何学习算法所能达到的期望泛化误差的下界；

正则化策略的目的就是降低方差，减小过拟合的发生。

对于L2norm：

因为公式中存在

因此L2正则化也称为权重衰减

2.在pytorch中怎么实现weight decay?

在Pytorch中，weight_decay是在优化器中实现的。例如：

class torch.optim.Adam(params, lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)

通过修改weight_decay=0来实现

3.在Adam优化器中，weight_decay的具体指代是？

参考博主系列文章：pytorch优化器详解：Adam

lr对应α；beta对应β1，β2；eps对应ϵ；

Adam优化器的源代码：

class Adam(Optimizer):
    r"""Implements Adam algorithm.

    It has been proposed in `Adam: A Method for Stochastic Optimization`_.
    The implementation of the L2 penalty follows changes proposed in
    `Decoupled Weight Decay Regularization`_.

    Args:
        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)
        amsgrad (boolean, optional): whether to use the AMSGrad variant of this
            algorithm from the paper `On the Convergence of Adam and Beyond`_
            (default: False)

    .. _Adam\: A Method for Stochastic Optimization:
        https://arxiv.org/abs/1412.6980
    .. _Decoupled Weight Decay Regularization:
        https://arxiv.org/abs/1711.05101
    .. _On the Convergence of Adam and Beyond:
        https://openreview.net/forum?id=ryQu7f-RZ
    """

    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
                 weight_decay=0, amsgrad=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 <= betas[0] < 1.0:
            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
        if not 0.0 <= weight_decay:
            raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
        defaults = dict(lr=lr, betas=betas, eps=eps,
                        weight_decay=weight_decay, amsgrad=amsgrad)
        super(Adam, self).__init__(params, defaults)

    def __setstate__(self, state):
        super(Adam, self).__setstate__(state)
        for group in self.param_groups:
            group.setdefault('amsgrad', False)

    @torch.no_grad()
    def step(self, closure=None):
        """Performs a single optimization step.

        Args:
            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 = []
            max_exp_avg_sqs = []
            state_steps = []
            beta1, beta2 = group['betas']

            for p in group['params']:
                if p.grad is not None:
                    params_with_grad.append(p)
                    if p.grad.is_sparse:
                        raise RuntimeError('Adam does not support sparse gradients, please consider SparseAdam instead')
                    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)
                        if group['amsgrad']:
                            # Maintains max of all exp. moving avg. of sq. grad. values
                            state['max_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'])

                    if group['amsgrad']:
                        max_exp_avg_sqs.append(state['max_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'])

            F.adam(params_with_grad,
                   grads,
                   exp_avgs,
                   exp_avg_sqs,
                   max_exp_avg_sqs,
                   state_steps,
                   amsgrad=group['amsgrad'],
                   beta1=beta1,
                   beta2=beta2,
                   lr=group['lr'],
                   weight_decay=group['weight_decay'],
                   eps=group['eps'])
        return loss

Adam函数接口

def adam(params: List[Tensor],
         grads: List[Tensor],
         exp_avgs: List[Tensor],
         exp_avg_sqs: List[Tensor],
         max_exp_avg_sqs: List[Tensor],
         state_steps: List[int],
         *,
         amsgrad: bool,
         beta1: float,
         beta2: float,
         lr: float,
         weight_decay: float,
         eps: float):
    r"""Functional API that performs Adam algorithm computation.

    See :class:`~torch.optim.Adam` for details.
    """

    for i, param in enumerate(params):

        grad = grads[i]
        exp_avg = exp_avgs[i]
        exp_avg_sq = exp_avg_sqs[i]
        step = state_steps[i]

        bias_correction1 = 1 - beta1 ** step
        bias_correction2 = 1 - beta2 ** step

        if weight_decay != 0:
            grad = grad.add(param, alpha=weight_decay)

        # Decay the first and second moment running average coefficient
        exp_avg.mul_(beta1).add_(grad, alpha=1 - beta1)
        exp_avg_sq.mul_(beta2).addcmul_(grad, grad, value=1 - beta2)
        if amsgrad:
            # Maintains the maximum of all 2nd moment running avg. till now
            torch.maximum(max_exp_avg_sqs[i], exp_avg_sq, out=max_exp_avg_sqs[i])
            # Use the max. for normalizing running avg. of gradient
            denom = (max_exp_avg_sqs[i].sqrt() / math.sqrt(bias_correction2)).add_(eps)
        else:
            denom = (exp_avg_sq.sqrt() / math.sqrt(bias_correction2)).add_(eps)

        step_size = lr / bias_correction1

        param.addcdiv_(exp_avg, denom, value=-step_size)

torch.add (input, value, out=None) 对输入张量input逐元素加上标量值value，并返回结果到一个新的张量out，即 out=tensor+value。