diff --git a/GPy/kern/_src/add.py b/GPy/kern/_src/add.py
index fdebdfac..3f00b22d 100644
--- a/GPy/kern/_src/add.py
+++ b/GPy/kern/_src/add.py
@@ -46,6 +46,9 @@ class Add(CombinationKernel):
     def update_gradients_diag(self, dL_dK, X):
         [p.update_gradients_diag(dL_dK, X) for p in self.parts]
 
+    def update_gradients_diag(self, dL_dKdiag, X):
+        [p.update_gradients_diag(dL_dKdiag, X[:,i_s]) for p, i_s in zip(self._parameters_, self.input_slices)]
+
     def gradients_X(self, dL_dK, X, X2=None):
         """Compute the gradient of the objective function with respect to X.
 
diff --git a/GPy/kern/_src/kern.py b/GPy/kern/_src/kern.py
index 8a24e24a..f8f2d588 100644
--- a/GPy/kern/_src/kern.py
+++ b/GPy/kern/_src/kern.py
@@ -62,6 +62,10 @@ class Kern(Parameterized):
     def gradients_X_diag(self, dL_dKdiag, X):
         raise NotImplementedError
 
+    def update_gradients_diag(self, dL_dKdiag, X):
+        """ update the gradients of all parameters when using only the diagonal elements of the covariance matrix"""
+        raise NotImplementedError
+
     def update_gradients_full(self, dL_dK, X, X2):
         """Set the gradients of all parameters when doing full (N) inference."""
         raise NotImplementedError