diff --git a/GPy/examples/BGPLVM_demo.py b/GPy/examples/BGPLVM_demo.py index 08e994f8..02092dbf 100644 --- a/GPy/examples/BGPLVM_demo.py +++ b/GPy/examples/BGPLVM_demo.py @@ -7,17 +7,17 @@ import GPy np.random.seed(123344) N = 10 -M = 3 -Q = 2 -D = 3 +M = 5 +Q = 3 +D = 4 #generate GPLVM-like data X = np.random.rand(N, Q) 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.rbf(Q) + GPy.kern.bias(Q) + GPy.kern.white(Q, 0.00001) -# k = GPy.kern.rbf_ARD(Q) + GPy.kern.white(Q, 0.00001) +# 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) m = GPy.models.Bayesian_GPLVM(Y, Q, kernel = k, M=M) m.constrain_positive('(rbf|bias|noise|white|S)') # m.constrain_fixed('S', 1) diff --git a/GPy/kern/rbf.py b/GPy/kern/rbf.py index a7c52180..ea76e4f5 100644 --- a/GPy/kern/rbf.py +++ b/GPy/kern/rbf.py @@ -38,7 +38,7 @@ class rbf(kernpart): if lengthscale is not None: assert lengthscale.shape == (1,) else: - lengthscale = np.ones(1) + lengthscale = np.ones(1) else: self.Nparam = self.D + 1 self.name = 'rbf_ARD' @@ -47,7 +47,7 @@ class rbf(kernpart): else: lengthscale = np.ones(self.D) - self._set_params(np.hstack((variance,lengthscale))) + self._set_params(np.hstack((variance,lengthscale))) #initialize cache self._Z, self._mu, self._S = np.empty(shape=(3,1)) @@ -69,7 +69,7 @@ class rbf(kernpart): if self.Nparam == 2: return ['variance','lengthscale'] else: - return ['variance']+['lengthscale_%i'%i for i in range(self.lengthscale.size)] + return ['variance']+['lengthscale_%i'%i for i in range(self.lengthscale.size)] def K(self,X,X2,target): if X2 is None: @@ -103,17 +103,10 @@ class rbf(kernpart): def dKdiag_dX(self,partial,X,target): pass - def _K_computations(self,X,X2): - if not (np.all(X==self._X) and np.all(X2==self._X2)): - self._X = X - self._X2 = X2 - if X2 is None: X2 = X - self._K_dist = X[:,None,:]-X2[None,:,:] # this can be computationally heavy - self._params = np.empty(shape=(1,0)) #ensure the next section gets called - if not np.all(self._params == self._get_params()): - self._params == self._get_params() - self._K_dist2 = np.square(self._K_dist/self.lengthscale) - self._K_dvar = np.exp(-0.5*self._K_dist2.sum(-1)) + + #---------------------------------------# + # PSI statistics # + #---------------------------------------# def psi0(self,Z,mu,S,target): target += self.variance @@ -133,7 +126,11 @@ class rbf(kernpart): denom_deriv = S[:,None,:]/(self.lengthscale**3+self.lengthscale*S[:,None,:]) d_length = self._psi1[:,:,None]*(self.lengthscale*np.square(self._psi1_dist/(self.lengthscale2+S[:,None,:])) + denom_deriv) target[0] += np.sum(partial*self._psi1/self.variance) - target[1] += np.sum(d_length*partial[:,:,None]) + dpsi1_dlength = d_length*partial[:,:,None] + if not self.ARD: + target[1] += dpsi1_dlength.sum() + else: + target[1:] += dpsi1_dlength.sum(0).sum(0) def dpsi1_dZ(self,partial,Z,mu,S,target): self._psi_computations(Z,mu,S) @@ -149,30 +146,52 @@ class rbf(kernpart): def psi2(self,Z,mu,S,target): self._psi_computations(Z,mu,S) - target += self._psi2.sum(0) #TODO: psi2 should be NxMxM (for het. noise) + target += self._psi2 def dpsi2_dtheta(self,partial,Z,mu,S,target): """Shape N,M,M,Ntheta""" self._psi_computations(Z,mu,S) - d_var = np.sum(2.*self._psi2/self.variance,0) + 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) - target[1] += np.sum(d_length*partial[:,:,None]) + 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,:,:,None]*dZ).sum(0).sum(0) + 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) + def dpsi2_dmuS(self,partial,Z,mu,S,target_mu,target_S): """Think N,M,M,Q """ self._psi_computations(Z,mu,S) tmp = self._psi2[:,:,:,None]/self.lengthscale2/self._psi2_denom - target_mu += (partial[None,:,:,None]*-tmp*2.*self._psi2_mudist).sum(1).sum(1) - target_S += (partial[None,:,:,None]*tmp*(2.*self._psi2_mudist_sq-1)).sum(1).sum(1) + target_mu += (partial[:,:,:,None]*-tmp*2.*self._psi2_mudist).sum(1).sum(1) + target_S += (partial[:,:,:,None]*tmp*(2.*self._psi2_mudist_sq-1)).sum(1).sum(1) + + + #---------------------------------------# + # Precomputations # + #---------------------------------------# + + def _K_computations(self,X,X2): + if not (np.all(X==self._X) and np.all(X2==self._X2)): + self._X = X + self._X2 = X2 + if X2 is None: X2 = X + self._K_dist = X[:,None,:]-X2[None,:,:] # this can be computationally heavy + self._params = np.empty(shape=(1,0)) #ensure the next section gets called + if not np.all(self._params == self._get_params()): + self._params == self._get_params() + self._K_dist2 = np.square(self._K_dist/self.lengthscale) + self._K_dvar = np.exp(-0.5*self._K_dist2.sum(-1)) def _psi_computations(self,Z,mu,S): #here are the "statistics" for psi1 and psi2 @@ -202,4 +221,3 @@ class rbf(kernpart): self._psi2 = np.square(self.variance)*np.exp(self._psi2_exponent) # N,M,M self._Z, self._mu, self._S = Z, mu,S - diff --git a/GPy/models/BGPLVM.py b/GPy/models/BGPLVM.py index 05dad318..db147944 100644 --- a/GPy/models/BGPLVM.py +++ b/GPy/models/BGPLVM.py @@ -58,5 +58,5 @@ class Bayesian_GPLVM(sparse_GP_regression, GPLVM): return np.hstack((dL_dmu.flatten(), dL_dS.flatten())) def _log_likelihood_gradients(self): - return np.hstack((self.dL_dmuS().flatten(), sparse_GP_regression.log_likelihood_gradients(self))) + return np.hstack((self.dL_dmuS().flatten(), sparse_GP_regression._log_likelihood_gradients(self)))