diff --git a/GPy/testing/minibatch_tests.py b/GPy/testing/minibatch_tests.py
index a5e9a884..7b39af95 100644
--- a/GPy/testing/minibatch_tests.py
+++ b/GPy/testing/minibatch_tests.py
@@ -132,15 +132,23 @@ class SparseGPMinibatchTest(unittest.TestCase):
         Q = Z.shape[1]
         m = GPy.models.sparse_gp_minibatch.SparseGPMiniBatch(self.X, self.Y, Z, GPy.kern.RBF(Q)+GPy.kern.Matern32(Q)+GPy.kern.Bias(Q), GPy.likelihoods.Gaussian(), missing_data=True, stochastic=False)
         assert(m.checkgrad())
+        m.optimize(max_iters=10)
+        assert(m.checkgrad())
 
         m = GPy.models.sparse_gp_minibatch.SparseGPMiniBatch(self.X, self.Y, Z, GPy.kern.RBF(Q)+GPy.kern.Matern32(Q)+GPy.kern.Bias(Q), GPy.likelihoods.Gaussian(), missing_data=True, stochastic=True)
         assert(m.checkgrad())
+        m.optimize(max_iters=10)
+        assert(m.checkgrad())
         
         m = GPy.models.sparse_gp_minibatch.SparseGPMiniBatch(self.X, self.Y, Z, GPy.kern.RBF(Q)+GPy.kern.Matern32(Q)+GPy.kern.Bias(Q), GPy.likelihoods.Gaussian(), missing_data=False, stochastic=False)
         assert(m.checkgrad())
+        m.optimize(max_iters=10)
+        assert(m.checkgrad())
         
         m = GPy.models.sparse_gp_minibatch.SparseGPMiniBatch(self.X, self.Y, Z, GPy.kern.RBF(Q)+GPy.kern.Matern32(Q)+GPy.kern.Bias(Q), GPy.likelihoods.Gaussian(), missing_data=False, stochastic=True)
         assert(m.checkgrad())
+        m.optimize(max_iters=10)
+        assert(m.checkgrad())
 
     def test_predict_missing_data(self):
         m = GPy.models.bayesian_gplvm_minibatch.BayesianGPLVMMiniBatch(self.Y, self.Q, X_variance=False, missing_data=True, stochastic=True, batchsize=self.Y.shape[1])