|View source on GitHub|
Create a random variable for Empirical.
tfp.edward2.Empirical( *args, **kwargs )
See Empirical for more details.
Original Docstring for Distribution
Tensorof shape [B1, ..., Bk, S, E1, ..., En]
,k, n >= 0
. Samples or batches of samples on which the distribution is based. The firstk
dimensions index into a batch of independent distributions. Length ofS
dimension determines number of samples in each multiset. The lastn` dimension represents samples for each distribution. n is specified by argument event_ndims.
0. number of dimensions for each event. When
0this distribution has scalar samples. When
1this distribution has vector-like samples.
Truedistribution parameters are checked for validity despite possibly degrading runtime performance. When
Falseinvalid inputs may silently render incorrect outputs.
True, statistics (e.g., mean, mode, variance) use the value
NaNto indicate the result is undefined. When
False, an exception is raised if one or more of the statistic's batch members are undefined.
strname prefixed to Ops created by this class.
ValueError: if the rank of
samplesis statically known and less than event_ndims + 1.