torch.Tensor.exponential_#

Tensor.exponential_(lambd=1,*,generator=None)→Tensor#

Fillsself tensor with elements drawn from the PDF (probability density function):

$$f(x)=\lambda e^{-\lambda x},x>0$$f(x)=λe−λx,x>0

Note

In probability theory, exponential distribution is supported on interval [0,$\inf$inf) (i.e.,$x>=0$x>=0)implying that zero can be sampled from the exponential distribution.However,torch.Tensor.exponential_() does not sample zero,which means that its actual support is the interval (0,$\inf$inf).

Note thattorch.distributions.exponential.Exponential() is supported on the interval [0,$\inf$inf) and can sample zero.