distribution¶
Distribution subpackage.
Submodules¶
Jax-based Bernoulli distribution representation. |
|
Jax-based distribution representation. |
|
Jax-based distribution representation. |
|
Jax-based Gaussian distribution representation. |
|
NumPy-based Bernoulli distribution representation. |
|
Numpy-based distribution representation. |
|
Numpy-based distribution representation. |
|
Numpy-based Gaussian distribution representation. |
|
Torch-based Bernoulli distribution representation. |
|
Torch-based categorical distribution representation. |
|
Torch implementation of the Dirichlet distribution representation. |
|
Torch-based Gaussian distribution representation. |
|
Torch-based mixture distribution representation. |
|
Sparse torch categorical distributions represented by grouped logits. |
Classes¶
Base class for Bernoulli distributions. |
|
Sample type for Bernoulli distributions. |
|
Base class for categorical distributions. |
|
Sample type for empirical second-order categorical distributions. |
|
Base class for Dirichlet distributions. |
|
Mixture distribution with Dirichlet components. |
|
Base class for distributions. |
|
Sample type for empirical second-order distributions. |
|
Base class for Gaussian distributions. |
|
Sample type for empirical second-order Gaussian distributions. |
|
Base class for mixture distributions. |
|
Base class for second-order distributions. |
Functions¶
Create a Bernoulli distribution from backend-specific probability data. |
|
Create a Bernoulli distribution from backend-specific logit data. |
|
Create a categorical distribution from backend-specific probability data. |
|
Create a categorical distribution from backend-specific logit data. |
|
Create a Dirichlet distribution from backend-specific alpha data. |
|
|
Create a Dirichlet mixture distribution from backend-specific alpha and weight data. |
Create a Gaussian distribution from backend-specific mean and variance data. |