|View source on GitHub|
Returns a callable that adds a random uniform perturbation to the input.
tfp.experimental.substrates.jax.mcmc.random_walk_uniform_fn( scale=1.0, name=None )
For more details on
Tensor or a list of
Tensors that should broadcast with state parts
current_state. The generated uniform perturbation is sampled as a
uniform point on the rectangle
Tensors of any shapes and
dtypescontrolling the upper and lower bound of the uniform proposal distribution.
strname prefixed to Ops created by this function. Default value: 'random_walk_uniform_fn'.
random_walk_uniform_fn: A callable accepting a Python
Tensors representing the state parts of the
intrepresenting the random seed used to generate the proposal. The callable returns the same-type
Tensors as the input and represents the proposal for the RWM algorithm.