psi-statistics for any kernels via Gaussian quadrature

GPy/kern/_src/kern.py

@@ -59,6 +59,9 @@ class Kern(Parameterized):
         self._sliced_X = 0
         self.useGPU = self._support_GPU and useGPU
         self._return_psi2_n_flag = ObsAr(np.zeros(1)).astype(bool)
+        
+        from .psi_comp import PSICOMP_GH
+        self.psicomp = PSICOMP_GH()
 
     @property
     def return_psi2_n(self):
@@ -90,11 +93,11 @@ class Kern(Parameterized):
     def Kdiag(self, X):
         raise NotImplementedError
     def psi0(self, Z, variational_posterior):
-        raise NotImplementedError
+        return self.psicomp.psicomputations(self, Z, variational_posterior)[0]
     def psi1(self, Z, variational_posterior):
-        raise NotImplementedError
+        return self.psicomp.psicomputations(self, Z, variational_posterior)[1]
     def psi2(self, Z, variational_posterior):
-        raise NotImplementedError
+        return self.psicomp.psicomputations(self, Z, variational_posterior)[2]
     def gradients_X(self, dL_dK, X, X2):
         raise NotImplementedError
     def gradients_X_diag(self, dL_dKdiag, X):
@@ -119,21 +122,22 @@ class Kern(Parameterized):
                         dL_dpsi1 * dpsi1_d{theta_i} +
                         dL_dpsi2 * dpsi2_d{theta_i}
         """
-        raise NotImplementedError
+        dtheta = self.psicomp.psiDerivativecomputations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior)[0]
+        self.gradient[:] = dtheta
 
     def gradients_Z_expectations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior):
         """
         Returns the derivative of the objective wrt Z, using the chain rule
         through the expectation variables.
         """
-        raise NotImplementedError
+        return self.psicomp.psiDerivativecomputations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior)[1]
 
     def gradients_qX_expectations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior):
         """
         Compute the gradients wrt the parameters of the variational
         distruibution q(X), chain-ruling via the expectations of the kernel
         """
-        raise NotImplementedError
+        return self.psicomp.psiDerivativecomputations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, variational_posterior)[2:]
 
     def plot(self, x=None, fignum=None, ax=None, title=None, plot_limits=None, resolution=None, **mpl_kwargs):
         """

GPy/kern/_src/psi_comp/__init__.py

@@ -8,9 +8,10 @@ from . import rbf_psi_comp
 from . import ssrbf_psi_comp
 from . import sslinear_psi_comp
 from . import linear_psi_comp
+from .gaussherm import PSICOMP_GH
 
 class PSICOMP_RBF(Pickleable):
-    @Cache_this(limit=2, ignore_args=(0,))
+    @Cache_this(limit=10, ignore_args=(0,))
     def psicomputations(self, variance, lengthscale, Z, variational_posterior):
         if isinstance(variational_posterior, variational.NormalPosterior):
             return rbf_psi_comp.psicomputations(variance, lengthscale, Z, variational_posterior)
@@ -19,7 +20,7 @@ class PSICOMP_RBF(Pickleable):
         else:
             raise ValueError("unknown distriubtion received for psi-statistics")
 
-    @Cache_this(limit=2, ignore_args=(0,1,2,3))
+    @Cache_this(limit=10, ignore_args=(0,1,2,3))
     def psiDerivativecomputations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, variance, lengthscale, Z, variational_posterior):
         if isinstance(variational_posterior, variational.NormalPosterior):
             return rbf_psi_comp.psiDerivativecomputations(dL_dpsi0, dL_dpsi1, dL_dpsi2, variance, lengthscale, Z, variational_posterior)
@@ -33,7 +34,7 @@ class PSICOMP_RBF(Pickleable):
 
 class PSICOMP_Linear(Pickleable):
 
-    @Cache_this(limit=2, ignore_args=(0,))
+    @Cache_this(limit=10, ignore_args=(0,))
     def psicomputations(self, variance, Z, variational_posterior):
         if isinstance(variational_posterior, variational.NormalPosterior):
             return linear_psi_comp.psicomputations(variance, Z, variational_posterior)
@@ -42,7 +43,7 @@ class PSICOMP_Linear(Pickleable):
         else:
             raise ValueError("unknown distriubtion received for psi-statistics")
 
-    @Cache_this(limit=2, ignore_args=(0,1,2,3))
+    @Cache_this(limit=10, ignore_args=(0,1,2,3))
     def psiDerivativecomputations(self, dL_dpsi0, dL_dpsi1, dL_dpsi2, variance, Z, variational_posterior):
         if isinstance(variational_posterior, variational.NormalPosterior):
             return linear_psi_comp.psiDerivativecomputations(dL_dpsi0, dL_dpsi1, dL_dpsi2, variance, Z, variational_posterior)

GPy/kern/_src/stationary.py

@@ -77,7 +77,7 @@ class Stationary(Kern):
     def dK_dr(self, r):
         raise NotImplementedError("implement derivative of the covariance function wrt r to use this class")
 
-    @Cache_this(limit=5, ignore_args=())
+    @Cache_this(limit=20, ignore_args=())
     def K(self, X, X2=None):
         """
         Kernel function applied on inputs X and X2.
@@ -89,7 +89,7 @@ class Stationary(Kern):
         r = self._scaled_dist(X, X2)
         return self.K_of_r(r)
 
-    @Cache_this(limit=3, ignore_args=())
+    @Cache_this(limit=20, ignore_args=())
     def dK_dr_via_X(self, X, X2):
         #a convenience function, so we can cache dK_dr
         return self.dK_dr(self._scaled_dist(X, X2))
@@ -114,7 +114,7 @@ class Stationary(Kern):
             r2 = np.clip(r2, 0, np.inf)
             return np.sqrt(r2)
 
-    @Cache_this(limit=5, ignore_args=())
+    @Cache_this(limit=20, ignore_args=())
     def _scaled_dist(self, X, X2=None):
         """
         Efficiently compute the scaled distance, r.