apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-09 03:52:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

derivatives of likelihood things now working for svgp

Browse source
This commit is contained in:
James Hensman 2015-03-24 13:58:41 +00:00
parent 611febe7eb
commit 53081c704d
3 changed files with 10 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
GPy/inference/latent_function_inference/svgp.py
View file

@ -47,6 +47,8 @@ class SVGP(LatentFunctionInference):
#rescale the F term if working on a batch #rescale the F term if working on a batch
F, dF_dmu, dF_dv = F*batch_scale, dF_dmu*batch_scale, dF_dv*batch_scale F, dF_dmu, dF_dv = F*batch_scale, dF_dmu*batch_scale, dF_dv*batch_scale
if dF_dthetaL is not None:
dF_dthetaL = dF_dthetaL.sum(1)*batch_scale
#derivatives of expected likelihood #derivatives of expected likelihood
Adv = A.T[:,:,None]*dF_dv[None,:,:] # As if dF_Dv is diagonal Adv = A.T[:,:,None]*dF_dv[None,:,:] # As if dF_Dv is diagonal

6
GPy/likelihoods/likelihood.py
View file

@ -177,7 +177,11 @@ class Likelihood(Parameterized):
if np.any(np.isnan(dF_dm)) or np.any(np.isinf(dF_dm)): if np.any(np.isnan(dF_dm)) or np.any(np.isinf(dF_dm)):
stop stop
dF_dtheta = None # Not yet implemented if self.size:
dF_dtheta = self.dlogpdf_dtheta(X, Y[:,None]) # Ntheta x (orig size) x N_{quad_points}
dF_dtheta = np.dot(dF_dtheta, gh_w)
else:
dF_dtheta = None # Not yet implemented
return F.reshape(*shape), dF_dm.reshape(*shape), dF_dv.reshape(*shape), dF_dtheta return F.reshape(*shape), dF_dm.reshape(*shape), dF_dv.reshape(*shape), dF_dtheta
def predictive_mean(self, mu, variance, Y_metadata=None): def predictive_mean(self, mu, variance, Y_metadata=None):

5
GPy/likelihoods/student_t.py
View file

@ -180,7 +180,8 @@ class StudentT(Likelihood):
:rtype: float :rtype: float
""" """
e = y - inv_link_f e = y - inv_link_f
dlogpdf_dvar = self.v*(e**2 - self.sigma2)/(2*self.sigma2*(self.sigma2*self.v + e**2)) e2 = np.square(e)
dlogpdf_dvar = self.v*(e2 - self.sigma2)/(2*self.sigma2*(self.sigma2*self.v + e2))
return dlogpdf_dvar return dlogpdf_dvar
def dlogpdf_dlink_dvar(self, inv_link_f, y, Y_metadata=None): def dlogpdf_dlink_dvar(self, inv_link_f, y, Y_metadata=None):
@ -226,7 +227,7 @@ class StudentT(Likelihood):
def dlogpdf_link_dtheta(self, f, y, Y_metadata=None): def dlogpdf_link_dtheta(self, f, y, Y_metadata=None):
dlogpdf_dvar = self.dlogpdf_link_dvar(f, y, Y_metadata=Y_metadata) dlogpdf_dvar = self.dlogpdf_link_dvar(f, y, Y_metadata=Y_metadata)
dlogpdf_dv = np.zeros_like(dlogpdf_dvar) #FIXME: Not done yet dlogpdf_dv = np.zeros_like(dlogpdf_dvar) #FIXME: Not done yet
return np.hstack((dlogpdf_dvar, dlogpdf_dv)) return np.array((dlogpdf_dvar, dlogpdf_dv))
def dlogpdf_dlink_dtheta(self, f, y, Y_metadata=None): def dlogpdf_dlink_dtheta(self, f, y, Y_metadata=None):
dlogpdf_dlink_dvar = self.dlogpdf_dlink_dvar(f, y, Y_metadata=Y_metadata) dlogpdf_dlink_dvar = self.dlogpdf_dlink_dvar(f, y, Y_metadata=Y_metadata)