https://github.com/GPflow/GPflow
Revision 1164235071397edf4dc0e227992d6fae4bb3a5ed authored by Eric Hammy on 11 February 2020, 14:27:49 UTC, committed by GitHub on 11 February 2020, 14:27:49 UTC
* Inconisistency on whether q_sqrt is triangular fixed.

Problem:
* KL divergence calculations only take lower triangle parts of q_sqrt in
their calculation (implying a lower triangular parameterisation of
covariance)
* Conditional calculations perform calculations using the whole of
q_sqrt.
* The end result is if you forgot to add the triangular transform
to the q_sqrt, your forward pass may be the same (if you initialise with
a triangular matrix), but your gradients will immediately stop q_sqrt
being triangular.

Fix:
* Conditional calulcations now only take the lower triangle parts of
q_sqrt in their calculation
1 parent 7275533
History
Tip revision: 1164235071397edf4dc0e227992d6fae4bb3a5ed authored by Eric Hammy on 11 February 2020, 14:27:49 UTC
Inconisistency on whether q_sqrt is triangular fixed. (#1223)
Tip revision: 1164235
File Mode Size
.circleci
.github
doc
gpflow
tests
.coveragerc -rw-r--r-- 283 bytes
.coveralls.yml -rw-r--r-- 23 bytes
.gitignore -rw-r--r-- 828 bytes
.pylintrc -rw-r--r-- 14.6 KB
GLOSSARY.md -rw-r--r-- 1.4 KB
LICENSE -rw-r--r-- 11.1 KB
MANIFEST.in -rw-r--r-- 182 bytes
Makefile -rw-r--r-- 597 bytes
README.md -rw-r--r-- 9.2 KB
RELEASE.md -rw-r--r-- 6.9 KB
VERSION -rw-r--r-- 9 bytes
codecov.yml -rw-r--r-- 274 bytes
contributing.md -rw-r--r-- 7.3 KB
docs_require.txt -rw-r--r-- 143 bytes
notebooks l--------- 21 bytes
setup.py -rw-r--r-- 2.2 KB
tests_requirements.txt -rw-r--r-- 219 bytes

README.md

back to top