Use more wide default init_dist in GaussianRandomWalk and AR and rais…

…e UserWarning when not explicitly defined

pymc/distributions/timeseries.py

@@ -227,7 +227,6 @@ class GaussianRandomWalk(distribution.Continuous):
         sigma > 0, innovation standard deviation, defaults to 1.0
     init_dist : unnamed distribution
         Univariate distribution of the initial value, created with the `.dist()` API.
-        Defaults to a unit Normal.
 
         .. warning:: init will be cloned, rendering them independent of the ones passed as input.
 
@@ -274,7 +273,12 @@ def dist(
 
         # If no scalar distribution is passed then initialize with a Normal of same mu and sigma
         if init_dist is None:
-            init_dist = Normal.dist(0, 1)
+            warnings.warn(
+                "Initial distribution not specified, defaulting to `Normal.dist(0, 100)`."
+                "You can specify an init_dist manually to suppress this warning.",
+                UserWarning,
+            )
+            init_dist = Normal.dist(0, 100)
         else:
             if not (
                 isinstance(init_dist, at.TensorVariable)
@@ -369,10 +373,10 @@ class AR(SymbolicDistribution):
     constant: bool, optional
         Whether the first element of rho should be used as a constant term in the AR
         process. Defaults to False
-    init_dist: unnamed distribution, optional
-        Scalar or vector distribution for initial values. Defaults to a unit Normal.
-        Distribution should be  created via the `.dist()` API, and have  dimension
-        (*size, ar_order). If not, it will be automatically resized.
+    init_dist: unnamed distribution
+        Scalar or vector distribution for initial values. Distribution should be
+        created via the `.dist()` API, and have  dimension (*size, ar_order). If not,
+        it will be automatically resized.
 
         .. warning:: init_dist will be cloned, rendering it independent of the one passed as input.
 
@@ -461,7 +465,13 @@ def dist(
                     f"got ndim_supp={init_dist.owner.op.ndim_supp}.",
                 )
         else:
-            init_dist = Normal.dist(0, 1, size=(*sigma.shape, ar_order))
+            warnings.warn(
+                "Initial distribution not specified, defaulting to "
+                "`Normal.dist(0, 100, shape=...)`. You can specify an init_dist "
+                "manually to suppress this warning.",
+                UserWarning,
+            )
+            init_dist = Normal.dist(0, 100, size=(*sigma.shape, ar_order))
 
         # Tell Aeppl to ignore init_dist, as it will be accounted for in the logp term
         init_dist = ignore_logprob(init_dist)

pymc/tests/test_distributions.py

@@ -2610,7 +2610,7 @@ def test_gaussianrandomwalk(self):
         def ref_logp(value, mu, sigma, steps):
             # Relying on fact that init will be normal by default
             return (
-                scipy.stats.norm.logpdf(value[0])
+                scipy.stats.norm.logpdf(value[0], 0, 100)  # default init_dist has a scale 100
                 + scipy.stats.norm.logpdf(np.diff(value), mu, sigma).sum()
             )
 

pymc/tests/test_distributions_timeseries.py

@@ -310,11 +310,11 @@ def test_batched_rhos(self):
         y_tp = np.random.randn(batch_size, steps)
         with Model() as t0:
             beta = Normal("beta", 0.0, 1.0, shape=(batch_size, ar_order), initval=beta_tp)
-            AR("y", beta, sigma=1.0, shape=(batch_size, steps), initval=y_tp)
+            AR("y", beta, sigma=1.0, init_dist=Normal.dist(0, 1), shape=(batch_size, steps), initval=y_tp)
         with Model() as t1:
             beta = Normal("beta", 0.0, 1.0, shape=(batch_size, ar_order), initval=beta_tp)
             for i in range(batch_size):
-                AR(f"y_{i}", beta[i], sigma=1.0, shape=steps, initval=y_tp[i])
+                AR(f"y_{i}", beta[i], init_dist=Normal.dist(0, 1), sigma=1.0, shape=steps, initval=y_tp[i])
 
         np.testing.assert_allclose(
             t0.compile_logp()(t0.initial_point()),
@@ -379,7 +379,7 @@ def test_batched_init_dist(self):
         beta_tp = aesara.shared(np.random.randn(ar_order), shape=(3,))
         y_tp = np.random.randn(batch_size, steps)
         with Model() as t0:
-            init_dist = Normal.dist(0.0, 1.0, size=(batch_size, ar_order))
+            init_dist = Normal.dist(0.0, 100.0, size=(batch_size, ar_order))
             AR("y", beta_tp, sigma=0.01, init_dist=init_dist, steps=steps, initval=y_tp)
         with Model() as t1:
             for i in range(batch_size):