apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-10 20:42:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

[classification] sparse gp inference for EPDTC

Browse source
This commit is contained in:
Max Zwiessele 2014-10-17 17:30:48 +01:00
parent 5ac7b2c524
commit 536adf0782
1 changed files with 7 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

7
GPy/inference/latent_function_inference/expectation_propagation_dtc.py
View file

@ -21,6 +21,13 @@ class EPDTC(LatentFunctionInference):
self.get_trYYT.limit = limit self.get_trYYT.limit = limit
self.get_YYTfactor.limit = limit self.get_YYTfactor.limit = limit
def on_optimization_start(self):
self._ep_approximation = None
def on_optimization_end(self):
# TODO: update approximation in the end as well? Maybe even with a switch?
pass
def _get_trYYT(self, Y): def _get_trYYT(self, Y):
return np.sum(np.square(Y)) return np.sum(np.square(Y))