https://github.com/GPflow/GPflow
Revision 6baeb43b1d68518e6ba0074e702d014f0fe85865 authored by jch5f on 15 June 2018, 10:31:27 UTC, committed by James Hensman on 15 June 2018, 10:31:27 UTC
* Add scaling to studentT conditional variance The conditional variance of the Student’s T distributions is proportional to the square of the scale of the distribution. See https://en.wikipedia.org/wiki/Student%27s_t-distribution#In_terms_of_sca ling_parameter_σ,_or_σ2. I’ve incorporated the correct scaling factor. * explicit scale dtype and tensor broadcasting Added an explicit data type for the Student’s T scale parameter, and made the broadcasting in the conditional_variance method explicit.
1 parent 916458e
Tip revision: 6baeb43b1d68518e6ba0074e702d014f0fe85865 authored by jch5f on 15 June 2018, 10:31:27 UTC
Likelihood/students t variance scaling (#777)
Likelihood/students t variance scaling (#777)
Tip revision: 6baeb43
File | Mode | Size |
---|---|---|
core | ||
models | ||
params | ||
saver | ||
training | ||
__init__.py | -rw-r--r-- | 1.6 KB |
_settings.py | -rw-r--r-- | 5.7 KB |
_version.py | -rw-r--r-- | 597 bytes |
actions.py | -rw-r--r-- | 11.9 KB |
conditionals.py | -rw-r--r-- | 9.6 KB |
decors.py | -rw-r--r-- | 7.2 KB |
expectations.py | -rw-r--r-- | 39.3 KB |
features.py | -rw-r--r-- | 6.6 KB |
gpflowrc | -rw-r--r-- | 525 bytes |
kernels.py | -rw-r--r-- | 27.5 KB |
kullback_leiblers.py | -rw-r--r-- | 3.8 KB |
likelihoods.py | -rw-r--r-- | 20.1 KB |
logdensities.py | -rw-r--r-- | 3.3 KB |
mean_functions.py | -rw-r--r-- | 5.4 KB |
misc.py | -rw-r--r-- | 7.4 KB |
priors.py | -rw-r--r-- | 4.5 KB |
probability_distributions.py | -rw-r--r-- | 1.7 KB |
quadrature.py | -rw-r--r-- | 6.0 KB |
session_manager.py | -rw-r--r-- | 4.3 KB |
test_util.py | -rw-r--r-- | 3.0 KB |
transforms.py | -rw-r--r-- | 12.5 KB |
Computing file changes ...