How to understand snr in LangevinCorrector?

[Flawless1202]

The code is here:

class LangevinCorrector(Corrector):
  def __init__(self, sde, score_fn, snr, n_steps):
    super().__init__(sde, score_fn, snr, n_steps)
    if not isinstance(sde, sde_lib.VPSDE) \
        and not isinstance(sde, sde_lib.VESDE) \
        and not isinstance(sde, sde_lib.subVPSDE):
      raise NotImplementedError(f"SDE class {sde.__class__.__name__} not yet supported.")

  def update_fn(self, x, t):
    sde = self.sde
    score_fn = self.score_fn
    n_steps = self.n_steps
    target_snr = self.snr
    if isinstance(sde, sde_lib.VPSDE) or isinstance(sde, sde_lib.subVPSDE):
      timestep = (t * (sde.N - 1) / sde.T).long()
      alpha = sde.alphas.to(t.device)[timestep]
    else:
      alpha = torch.ones_like(t)

    for i in range(n_steps):
      grad = score_fn(x, t)
      noise = torch.randn_like(x)
      grad_norm = torch.norm(grad.reshape(grad.shape[0], -1), dim=-1).mean()
      noise_norm = torch.norm(noise.reshape(noise.shape[0], -1), dim=-1).mean()
      step_size = (target_snr * noise_norm / grad_norm) ** 2 * 2 * alpha
      x_mean = x + step_size[:, None, None, None] * grad
      x = x_mean + torch.sqrt(step_size * 2)[:, None, None, None] * noise

    return x, x_mean

Could you please give me some explanation or references? Thx a lot! @yang-song @patrickvonplaten

[4X-V-5]

snr is the variable r in Algorithm 4 and Algorithm 5 in the original paper