fix: tutorials test error handling, fix bugs in tutorials

tests/tutorials_test.py

@@ -32,8 +32,10 @@ def test_tutorials(notebook_path):
             if "Requested MovieWriter" in str(e):
                 print("Skipping error in movie writer.")
             else:
-                raise CellExecutionError from e
+                raise RuntimeError(
+                    f"Error executing the notebook {notebook_path}: {e}"
+                ) from e
         except Exception as e:
-            raise AssertionError(
+            raise RuntimeError(
                 f"Error executing the notebook {notebook_path}: {e}"
             ) from e

tutorials/12_iid_data_and_permutation_invariant_embeddings.ipynb

@@ -226,8 +226,8 @@
     }
    ],
    "source": [
-    "# Train SNLE.\n",
-    "inferer = SNLE(prior, show_progress_bars=True, density_estimator=\"mdn\")\n",
+    "# Train NLE.\n",
+    "inferer = NLE(prior, show_progress_bars=True, density_estimator=\"mdn\")\n",
     "theta, x = simulate_for_sbi(simulator, prior, 10000, simulation_batch_size=1000)\n",
     "inferer.append_simulations(theta, x).train(training_batch_size=1000);"
    ]
@@ -310,9 +310,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The pairplot above already indicates that (S)NLE is well able to obtain accurate posterior samples also for increasing number of trials (note that we trained the single-round version of SNLE so that we did not have to re-train it for new $x_o$).\n",
+    "The pairplot above already indicates that (S)NLE is well able to obtain accurate posterior samples also for increasing number of trials (note that we trained the single-round version of NLE so that we did not have to re-train it for new $x_o$).\n",
     "\n",
-    "Quantitatively we can measure the accuracy of SNLE by calculating the `c2st` score between SNLE and the true posterior samples, where the best accuracy is perfect for `0.5`:\n"
+    "Quantitatively we can measure the accuracy of NLE by calculating the `c2st` score between NLE and the true posterior samples, where the best accuracy is perfect for `0.5`:\n"
    ]
   },
   {

tutorials/15_importance_sampled_posteriors.ipynb

@@ -161,7 +161,11 @@
     "print(\"observations.shape\", observation.shape)\n",
     "\n",
     "# sample from posterior\n",
-    "theta_inferred = posterior.sample((10_000,))"
+    "theta_inferred = posterior.sample((10_000,))\n",
+    "\n",
+    "# get samples from ground-truth posterior\n",
+    "gt_samples = MultivariateNormal(observation, eye(2)).sample((len(theta_inferred) * 5,))\n",
+    "gt_samples = gt_samples[prior.support.check(gt_samples)][:len(theta_inferred)]"
    ]
   },
   {