View source on GitHub |
Compute exponentially weighted moving {mean,variance} of a streaming value.
tf.contrib.distributions.assign_moving_mean_variance(
mean_var, variance_var, value, decay, name=None
)
The value
updated exponentially weighted moving mean_var
and
variance_var
are given by the following recurrence relations:
variance_var = decay * (variance_var + (1-decay) * (value - mean_var)**2)
mean_var = decay * mean_var + (1 - decay) * value
For derivation justification, see [Finch (2009; Eq. 143)][1].
Args | |
---|---|
mean_var
|
float -like Variable representing the exponentially weighted
moving mean. Same shape as variance_var and value .
|
variance_var
|
float -like Variable representing the
exponentially weighted moving variance. Same shape as mean_var and
value .
|
value
|
float -like Tensor . Same shape as mean_var and variance_var .
|
decay
|
A float -like Tensor . The moving mean decay. Typically close to
1. , e.g., 0.999 .
|
name
|
Optional name of the returned operation. |
Returns | |
---|---|
mean_var
|
Variable representing the value -updated exponentially weighted
moving mean.
|
variance_var
|
Variable representing the value -updated
exponentially weighted moving variance.
|
Raises | |
---|---|
TypeError
|
if mean_var does not have float type dtype .
|
TypeError
|
if mean_var , variance_var , value , decay have different
base_dtype .
|
References
[1]: Tony Finch. Incremental calculation of weighted mean and variance. Technical Report, 2009. http://people.ds.cam.ac.uk/fanf2/hermes/doc/antiforgery/stats.pdf