python - sample() 和 rsample() 有什么区别？

Question

当我从 PyTorch 的分布中采样时，sample和 rsample似乎给出了类似的结果:

import torch, seaborn as sns

x = torch.distributions.Normal(torch.tensor([0.0]), torch.tensor([1.0]))

sns.distplot(x.sample((100000,))) sns.distplot(x.rsample((100000,)))

我应该什么时候使用 sample() ，我应该什么时候使用 rsample() ?

Answer 1

使用 rsample允许 pathwise derivatives :

The other way to implement these stochastic/policy gradients would be to use the reparameterization trick from the rsample() method, where the parameterized random variable can be constructed via a parameterized deterministic function of a parameter-free random variable. The reparameterized sample therefore becomes differentiable.