all kernels working fine with the psi statistics now

GPy/examples/BGPLVM_demo.py

@@ -6,8 +6,8 @@ import pylab as pb
 import GPy
 np.random.seed(123344)
 
-N = 3
+N = 10
-M = 2
+M = 3
 Q = 2
 D = 4
 #generate GPLVM-like data
@@ -16,7 +16,7 @@ k = GPy.kern.rbf(Q) + GPy.kern.white(Q, 0.00001)
 K = k.K(X)
 Y = np.random.multivariate_normal(np.zeros(N),K,D).T
 
-k = GPy.kern.bias(Q) #+ GPy.kern.white(Q)
+k = GPy.kern.linear(Q, ARD = True) + GPy.kern.white(Q)
 # k = GPy.kern.rbf(Q) + GPy.kern.rbf(Q) + GPy.kern.white(Q)
 # k = GPy.kern.rbf(Q) + GPy.kern.bias(Q) + GPy.kern.white(Q, 0.00001)
 # k = GPy.kern.rbf(Q, ARD = False)  + GPy.kern.white(Q, 0.00001)

GPy/examples/oil_flow_demo.py

@@ -32,7 +32,7 @@ Y -= Y.mean(axis=0)
 # Y /= Y.std(axis=0)
 
 Q = 5
-k = GPy.kern.linear(Q, ARD = False) + GPy.kern.white(Q)
+k = GPy.kern.linear(Q, ARD = True) + GPy.kern.white(Q)
 m = GPy.models.Bayesian_GPLVM(Y, Q, kernel = k, M = 20)
 m.constrain_positive('(rbf|bias|S|linear|white|noise)')
 
@@ -41,7 +41,7 @@ m.constrain_positive('(rbf|bias|S|linear|white|noise)')
 # m.unconstrain('white')
 # m.constrain_bounded('white', 1e-6, 10.0)
 # plot_oil(m.X, np.array([1,1]), labels, 'PCA initialization')
-# m.optimize(messages = True)
+m.optimize(messages = True)
 # m.optimize('tnc', messages = True)
 # plot_oil(m.X, m.kern.parts[0].lengthscale, labels, 'B-GPLVM')
 # # pb.figure()

GPy/kern/linear.py

@@ -90,22 +90,19 @@ class linear(kernpart):
 
     def psi0(self,Z,mu,S,target):
         self._psi_computations(Z,mu,S)
-        target += np.sum(self.variances*self.mu2_S)
+        target += np.sum(self.variances*self.mu2_S,1)
 
     def dpsi0_dtheta(self,partial,Z,mu,S,target):
         self._psi_computations(Z,mu,S)
-        tmp = (partial[:, None] * (np.sum(self.mu2_S,0)))
+        tmp = partial[:, None] * self.mu2_S
         if self.ARD:
             target += tmp.sum(0)
         else:
             target += tmp.sum()
 
     def dpsi0_dmuS(self,partial, Z,mu,S,target_mu,target_S):
-        target_mu += np.sum(partial[:, None],0) * (2.0*mu*self.variances)
+        target_mu += partial[:, None] * (2.0*mu*self.variances)
-        target_S += np.sum(partial[:, None] * self.variances, 0)
+        target_S += partial[:, None] * self.variances
-
-    def dpsi0_dZ(self,Z,mu,S,target):
-        pass
 
     def psi1(self,Z,mu,S,target):
         """the variance, it does nothing"""
@@ -149,7 +146,7 @@ class linear(kernpart):
     def dpsi2_dZ(self,partial,Z,mu,S,target):
         self._psi_computations(Z,mu,S)
         mu2_S = np.sum(self.mu2_S,0)# Q,
-        target += (partial[:,:,:,None]* (Z * mu2_S * np.square(self.variances))).sum(0).sum(1)
+        target += (partial[:,:,:,None] * (self.mu2_S[:,None,None,:]*(Z*np.square(self.variances)[None,:])[None,None,:,:])).sum(0).sum(1)
 
     #---------------------------------------#
     #            Precomputations            #

GPy/kern/rbf.py

@@ -155,21 +155,20 @@ class rbf(kernpart):
         self._psi_computations(Z,mu,S)
         d_var = 2.*self._psi2/self.variance
         d_length = self._psi2[:,:,:,None]*(0.5*self._psi2_Zdist_sq*self._psi2_denom + 2.*self._psi2_mudist_sq + 2.*S[:,None,None,:]/self.lengthscale2)/(self.lengthscale*self._psi2_denom)
-        d_length = d_length.sum(0)
+
         target[0] += np.sum(partial*d_var)
         dpsi2_dlength = d_length*partial[:,:,:,None]
         if not self.ARD:
             target[1] += dpsi2_dlength.sum()
         else:
             target[1:] += dpsi2_dlength.sum(0).sum(0).sum(0)
-
+            
     def dpsi2_dZ(self,partial,Z,mu,S,target):
         self._psi_computations(Z,mu,S)
         term1 = 0.5*self._psi2_Zdist/self.lengthscale2 # M, M, Q
         term2 = self._psi2_mudist/self._psi2_denom/self.lengthscale2 # N, M, M, Q
         dZ = self._psi2[:,:,:,None] * (term1[None] + term2)
-        target += (partial[:,:,:,None]*dZ).sum(0).sum(0) # <----------------- TODO not sure about the first ':' here, should be a None (WAS a none in the debug branch)
+        target += (partial[:,:,:,None]*dZ).sum(0).sum(0)
-
 
     def dpsi2_dmuS(self,partial,Z,mu,S,target_mu,target_S):
         """Think N,M,M,Q """

GPy/models/sparse_GP.py

@@ -34,7 +34,7 @@ class sparse_GP(GP):
     """
 
     def __init__(self, X, likelihood, kernel, Z, X_uncertainty=None, Xslices=None,Zslices=None, normalize_X=False):
-        self.scale_factor = 1.0# a scaling factor to help keep the algorithm stable
+        self.scale_factor = 100.0# a scaling factor to help keep the algorithm stable
 
         self.Z = Z
         self.Zslices = Zslices