Remove EllipticalSlice sampler

Closes pymc-devs#5137

RELEASE-NOTES.md

@@ -14,7 +14,6 @@ Instead update the vNext section until 4.0.0 is out.
 We plan to get these working again, but at this point their inner workings have not been refactored.
 - Timeseries distributions (see [#4642](https://github.com/pymc-devs/pymc/issues/4642))
 - Nested Mixture distributions (see [#5533](https://github.com/pymc-devs/pymc/issues/5533))
-- Elliptical slice sampling (see [#5137](https://github.com/pymc-devs/pymc/issues/5137))
 - `pm.sample_posterior_predictive_w` (see [#4807](https://github.com/pymc-devs/pymc/issues/4807))
 - Partially observed Multivariate distributions (see [#5260](https://github.com/pymc-devs/pymc/issues/5260))
 
@@ -32,6 +31,7 @@ Signature and default parameters changed for several distributions (see [#5628](
     - `pm.AsymmetricLaplace` positional arguments re-ordered
     - `pm.AsymmetricLaplace` now requires `mu` to be specified (no longer defaults to 0)
 - BART was removed [#5566](https://github.com/pymc-devs/pymc/pull/5566). It is now available from [pymc-experimental](https://github.com/pymc-devs/pymc-experimental)
+- The `pm.EllipticalSlice` sampler was removed (see [#5756](https://github.com/pymc-devs/pymc/issues/5756)).
 - `BaseStochasticGradient` was removed (see [#5630](https://github.com/pymc-devs/pymc/pull/5630))
 - ⚠ The library is now named, installed and imported as "pymc". For example: `pip install pymc`.
 - ⚠ Theano-PyMC has been replaced with Aesara, so all external references to `theano`, `tt`, and `pymc3.theanof` need to be replaced with `aesara`, `at`, and `pymc.aesaraf` (see [4471](https://github.com/pymc-devs/pymc/pull/4471)).

docs/source/api/samplers.rst

@@ -70,5 +70,4 @@ Other step methods
    :toctree: generated/
 
    CompoundStep
-   EllipticalSlice
    Slice

pymc/step_methods/__init__.py

@@ -13,7 +13,6 @@
 #   limitations under the License.
 
 from pymc.step_methods.compound import CompoundStep
-from pymc.step_methods.elliptical_slice import EllipticalSlice
 from pymc.step_methods.hmc import NUTS, HamiltonianMC
 from pymc.step_methods.metropolis import (
     BinaryGibbsMetropolis,

pymc/tests/models.py

@@ -163,32 +163,6 @@ def mv_simple_discrete():
     return model.initial_point(), model, (mu, C)
 
 
-def mv_prior_simple():
-    n = 3
-    noise = 0.1
-    X = np.linspace(0, 1, n)[:, None]
-
-    K = pm.gp.cov.ExpQuad(1, 1)(X).eval()
-    L = np.linalg.cholesky(K)
-    K_noise = K + noise * np.eye(n)
-    obs = floatX_array([-0.1, 0.5, 1.1])
-
-    # Posterior mean
-    L_noise = np.linalg.cholesky(K_noise)
-    alpha = np.linalg.solve(L_noise.T, np.linalg.solve(L_noise, obs))
-    mu_post = np.dot(K.T, alpha)
-
-    # Posterior standard deviation
-    v = np.linalg.solve(L_noise, K)
-    std_post = (K - np.dot(v.T, v)).diagonal() ** 0.5
-
-    with pm.Model() as model:
-        x = pm.Flat("x", size=n)
-        x_obs = pm.MvNormal("x_obs", observed=obs, mu=x, cov=noise * np.eye(n))
-
-    return model.initial_point(), model, (K, L, mu_post, std_post, noise)
-
-
 def non_normal(n=2):
     with pm.Model() as model:
         pm.Beta("x", 3, 3, size=n, transform=None)

pymc/tests/test_step.py

@@ -50,7 +50,6 @@
     CompoundStep,
     DEMetropolis,
     DEMetropolisZ,
-    EllipticalSlice,
     HamiltonianMC,
     Metropolis,
     MultivariateNormalProposal,
@@ -62,7 +61,6 @@
 from pymc.step_methods.mlda import extract_Q_estimate
 from pymc.tests.checks import close_to
 from pymc.tests.models import (
-    mv_prior_simple,
     mv_simple,
     mv_simple_coarse,
     mv_simple_discrete,
@@ -154,19 +152,6 @@ def test_step_categorical(self):
             idata = sample(8000, tune=0, step=step, start=start, model=model, random_seed=1)
             self.check_stat(check, idata, step.__class__.__name__)
 
-    @pytest.mark.xfail(reason="EllipticalSlice not refactored for v4")
-    def test_step_elliptical_slice(self):
-        start, model, (K, L, mu, std, noise) = mv_prior_simple()
-        unc = noise**0.5
-        check = (("x", np.mean, mu, unc / 10.0), ("x", np.std, std, unc / 10.0))
-        with model:
-            steps = (EllipticalSlice(prior_cov=K), EllipticalSlice(prior_chol=L))
-        for step in steps:
-            idata = sample(
-                5000, tune=0, step=step, start=start, model=model, random_seed=1, chains=1
-            )
-            self.check_stat(check, idata, step.__class__.__name__)
-
 
 class TestMetropolisProposal:
     def test_proposal_choice(self):
@@ -1311,7 +1296,6 @@ class TestRVsAssignmentSteps:
             (HamiltonianMC, {}),
             (Metropolis, {}),
             (Slice, {}),
-            (EllipticalSlice, {"prior_cov": np.eye(1)}),
             (DEMetropolis, {}),
             (DEMetropolisZ, {}),
             # (MLDA, {}),  # TODO

scripts/run_mypy.py

@@ -56,7 +56,6 @@
 pymc/stats/__init__.py
 pymc/step_methods/__init__.py
 pymc/step_methods/compound.py
-pymc/step_methods/elliptical_slice.py
 pymc/step_methods/hmc/__init__.py
 pymc/step_methods/hmc/base_hmc.py
 pymc/step_methods/hmc/hmc.py