[spgp minibatch] linear calls the right psicomps and add kernel

GPy/core/sparse_gp.py

@@ -119,9 +119,10 @@ class SparseGP(GP):
         if there is missing data, each dimension has its own full_cov of shape NxNxD, and if full_cov is of,
         we take only the diagonal elements across N.
 
-        For uncertain inputs, the SparseGP bound produces a full covariance structure across D, so for full_cov we
+        For uncertain inputs, the SparseGP bound produces cannot predict the full covariance matrix full_cov for now.
-        return a NxDxD matrix and in the not full_cov case, we return the diagonal elements across D (NxD).
+        The implementation of that will follow. However, for each dimension the
-        This is for both with and without missing data. See for missing data SparseGP implementation py:class:'~GPy.models.sparse_gp_minibatch.SparseGPMiniBatch'.
+        covariance changes, so if full_cov is False (standard), we return the variance
+        for each dimension [NxD].
         """
 
         if kern is None: kern = self.kern
@@ -158,6 +159,7 @@ class SparseGP(GP):
             mu = np.dot(psi1_star, la) # TODO: dimensions?
 
             if full_cov:
+                raise NotImplementedError, "Full covariance for Sparse GP predicted with uncertain inputs not implemented yet."
                 var = np.empty((Xnew.shape[0], la.shape[1], la.shape[1]))
                 di = np.diag_indices(la.shape[1])
             else:

GPy/kern/_src/add.py

@@ -85,15 +85,15 @@ class Add(CombinationKernel):
         [target.__iadd__(p.gradients_XX_diag(dL_dKdiag, X)) for p in self.parts]
         return target
 
-    @Cache_this(limit=2, force_kwargs=['which_parts'])
+    @Cache_this(limit=1, force_kwargs=['which_parts'])
     def psi0(self, Z, variational_posterior):
         return reduce(np.add, (p.psi0(Z, variational_posterior) for p in self.parts))
 
-    @Cache_this(limit=2, force_kwargs=['which_parts'])
+    @Cache_this(limit=1, force_kwargs=['which_parts'])
     def psi1(self, Z, variational_posterior):
         return reduce(np.add, (p.psi1(Z, variational_posterior) for p in self.parts))
 
-    @Cache_this(limit=2, force_kwargs=['which_parts'])
+    @Cache_this(limit=1, force_kwargs=['which_parts'])
     def psi2(self, Z, variational_posterior):
         psi2 = reduce(np.add, (p.psi2(Z, variational_posterior) for p in self.parts))
         #return psi2
@@ -128,7 +128,7 @@ class Add(CombinationKernel):
                 raise NotImplementedError("psi2 cannot be computed for this kernel")
         return psi2
 
-    @Cache_this(limit=2, force_kwargs=['which_parts'])
+    @Cache_this(limit=1, force_kwargs=['which_parts'])
     def psi2n(self, Z, variational_posterior):
         psi2 = reduce(np.add, (p.psi2n(Z, variational_posterior) for p in self.parts))
         #return psi2

GPy/kern/_src/linear.py

@@ -125,6 +125,9 @@ class Linear(Kern):
     def psi2(self, Z, variational_posterior):
         return self.psicomp.psicomputations(self.variances, Z, variational_posterior)[2]
 
+    def psi2n(self, Z, variational_posterior):
+        return self.psicomp.psicomputations(self.variances, Z, variational_posterior, return_psi2_n=True)[2]
+
     def update_gradients_expectations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior):
         dL_dvar = self.psicomp.psiDerivativecomputations(dL_dpsi0, dL_dpsi1, dL_dpsi2, self.variances, Z, variational_posterior)[0]
         if self.ARD:

GPy/kern/_src/psi_comp/__init__.py

@@ -35,9 +35,9 @@ class PSICOMP_RBF(Pickleable):
 class PSICOMP_Linear(Pickleable):
 
     @Cache_this(limit=2, ignore_args=(0,))
-    def psicomputations(self, variance, Z, variational_posterior):
+    def psicomputations(self, variance, Z, variational_posterior, return_psi2_n=False):
         if isinstance(variational_posterior, variational.NormalPosterior):
-            return linear_psi_comp.psicomputations(variance, Z, variational_posterior)
+            return linear_psi_comp.psicomputations(variance, Z, variational_posterior, return_psi2_n=return_psi2_n)
         elif isinstance(variational_posterior, variational.SpikeAndSlabPosterior):
             return sslinear_psi_comp.psicomputations(variance, Z, variational_posterior)
         else:

GPy/models/sparse_gp_minibatch.py

@@ -171,8 +171,7 @@ class SparseGPMiniBatch(SparseGP):
                                                 variational_posterior=self.X,
                                                 Z=self.Z, dL_dpsi0=full_values['dL_dpsi0'],
                                                 dL_dpsi1=full_values['dL_dpsi1'],
-                                                dL_dpsi2=full_values['dL_dpsi2'],
+                                                dL_dpsi2=full_values['dL_dpsi2'])
-                                                psi0=self.psi0, psi1=self.psi1, psi2=self.psi2)
             self.kern.gradient += kgrad
 
 
@@ -182,8 +181,7 @@ class SparseGPMiniBatch(SparseGP):
                                             variational_posterior=self.X,
                                             Z=self.Z, dL_dpsi0=full_values['dL_dpsi0'],
                                             dL_dpsi1=full_values['dL_dpsi1'],
-                                            dL_dpsi2=full_values['dL_dpsi2'],
+                                            dL_dpsi2=full_values['dL_dpsi2'])
-                                            psi0=self.psi0, psi1=self.psi1, psi2=self.psi2)
         else:
             #gradients wrt kernel
             self.kern.update_gradients_diag(full_values['dL_dKdiag'], self.X)