diglm¶
The diglm
module implements a Deep Invertible Generalized Linear Model.
Diglm¶
Diglm: Deeply Invertible Generalized Linear Model
-
class
diglm.
Diglm
(bijector, glm, num_features, name='diglm', **kwargs)[source]¶ Deep Invertible Generalized Linear Model using tensorflow_probability. This class implements the model described by Nalisnick et al. in `Hybrid Models with Deep and Invertible Features<https://arxiv.org/abs/1902.02767>`_. See the original article for a detailed discussion of the model, its pros and cons and its possible applications. Inherits from tensorflow_probability.distributions.JointDistributionsNamed.
- Parameters
bijector (tensorflow_probability.bijectors.Bijector) – Bijector with learnable parameters for the invertible tranformation.
glm (tensorflow_probability.glm.ExponentialFamily) – Generalized linear model.
num_feature – Dimensions of features space.
**kwargs –
Other arguments for JointDitributionNamed.
-
property
bijector
¶ The bijector
-
cross_entropy
(other, name='cross_entropy')¶ Computes the (Shannon) cross entropy.
Denote this distribution (self) by P and the other distribution by Q. Assuming P, Q are absolutely continuous with respect to one another and permit densities p(x) dr(x) and q(x) dr(x), (Shannon) cross entropy is defined as:
`none H[P, Q] = E_p[-log q(X)] = -int_F p(x) log q(x) dr(x) `
where F denotes the support of the random variable X ~ P.
- Args:
other: tfp.distributions.Distribution instance. name: Python str prepended to names of ops created by this function.
- Returns:
- cross_entropy: self.dtype Tensor with shape [B1, …, Bn]
representing n different calculations of (Shannon) cross entropy.
-
eta_from_features
(features)[source]¶ Compute predicted linear response transforming features in latent space.
- Parameters
features (tensorflow.Tensor) – Model features.
- Returns
Predicted linear response.
- Return type
tensorflow.Tensor
-
property
glm
¶ Generalized Linear Model
-
kl_divergence
(other, name='kl_divergence')¶ Computes the Kullback–Leibler divergence.
Denote this distribution (self) by p and the other distribution by q. Assuming p, q are absolutely continuous with respect to reference measure r, the KL divergence is defined as:
```none KL[p, q] = E_p[log(p(X)/q(X))]
= -int_F p(x) log q(x) dr(x) + int_F p(x) log p(x) dr(x) = H[p, q] - H[p]
where F denotes the support of the random variable X ~ p, H[., .] denotes (Shannon) cross entropy, and H[.] denotes (Shannon) entropy.
- Args:
other: tfp.distributions.Distribution instance. name: Python str prepended to names of ops created by this function.
- Returns:
- kl_divergence: self.dtype Tensor with shape [B1, …, Bn]
representing n different calculations of the Kullback-Leibler divergence.
-
latent_features
(features)[source]¶ Compute latent variables from features.
- Parameters
features (tensorflow.Tensor) – Model features.
- Returns
Transformed feature in latent space.
- Return type
tensorflow.Tensor
-
property
num_features
¶ Number of features