layer_autoregressive_transform | R Documentation |
layer_autoregressive
.Following Papamakarios et al. (2017), given an autoregressive model p(x) with conditional distributions in the location-scale family, we can construct a normalizing flow for p(x).
layer_autoregressive_transform(object, made, ...)
object |
What to compose the new
|
made |
A |
... |
Additional parameters passed to Keras Layer. |
Specifically, suppose made is a [layer_autoregressive()]
– a layer implementing
a Masked Autoencoder for Distribution Estimation (MADE) – that computes location
and log-scale parameters made(x)[i] for each input x[i]. Then we can represent
the autoregressive model p(x) as x = f(u) where u is drawn
from from some base distribution and where f is an invertible and
differentiable function (i.e., a Bijector) and f^{-1}(x) is defined by:
library(tensorflow) library(zeallot) f_inverse <- function(x) { c(shift, log_scale) %<-% tf$unstack(made(x), 2, axis = -1L) (x - shift) * tf$math$exp(-log_scale) }
Given a layer_autoregressive()
made, a layer_autoregressive_transform()
transforms an input tfd_*
p(u) to an output tfd_*
p(x) where
x = f(u).
a Keras layer
tfb_masked_autoregressive_flow()
and layer_autoregressive()
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.