Get q(x_{t+1} | x_t), the one-step posterior efficiently. Args: qt_plus_1: an array of floats specifying a distribution over p(x_0).

Get q(x_{t+1} | x_t), the one-step posterior efficiently. Args: qt_plus_1: an array of floats specifying a distribution over p(x_0).

Samples from q(x_{t+1} | x_0), then computes q(x_t | x_{t+1}, x_0). Args: x_0: an array containing x_0 samples. These are expected t

Samples from q(x_{t+1} | x_0), then computes q(x_t | x_{t+1}, x_0). Args: x_0: an array containing x_0 samples. These are expected t

Draws a sample from the stationary distribution (q(x_T)).

Draws a sample from the stationary distribution (q(x_T)).

Samples batches of time steps to use.

This function is a canonical implementation of self-BLEU. The deviation from the above one is that the references are ALL THE REST sentences

Returns probs for the stationary distribution.

Returns probs for the stationary distribution.

Returns true if get() is implemented/efficient.

Returns true if get() is implemented/efficient.

Returns true if custom_product_fn is implemented. The ontology of efficient_get and efficient_inference is this: * if efficient_infe

Returns true if custom_product_fn is implemented. The ontology of efficient_get and efficient_inference is this: * if efficient_infe