Document the rest of the specific optimizer module APIs (#158669)

Pull Request resolved: https://github.com/pytorch/pytorch/pull/158669
Approved by: https://github.com/albanD
ghstack dependencies: #158483

docs/source/conf.py

@@ -1840,25 +1840,9 @@ coverage_ignore_functions = [
     "check_export_model_diff",
     "verify",
     "verify_aten_graph",
-    # torch.optim.adamax
-    "adamax",
-    # torch.optim.adamw
-    "adamw",
-    # torch.optim.asgd
-    "asgd",
-    # torch.optim.nadam
-    "nadam",
     # torch.optim.optimizer
     "register_optimizer_step_post_hook",
     "register_optimizer_step_pre_hook",
-    # torch.optim.radam
-    "radam",
-    # torch.optim.rmsprop
-    "rmsprop",
-    # torch.optim.rprop
-    "rprop",
-    # torch.optim.sgd
-    "sgd",
     # torch.optim.swa_utils
     "get_ema_avg_fn",
     "get_ema_multi_avg_fn",
@@ -3131,23 +3115,8 @@ coverage_ignore_classes = [
     "ReduceLROnPlateau",
     "SequentialLR",
     "StepLR",
-    # torch.optim.nadam
-    "NAdam",
     # torch.optim.optimizer
     "Optimizer",
-    # torch.optim.radam
-    "RAdam",
-    # torch.optim.rmsprop
-    "RMSprop",
-    # torch.optim.rprop
-    "Rprop",
-    # torch.optim.sgd
-    "SGD",
-    # torch.optim.sparse_adam
-    "SparseAdam",
-    # torch.optim.swa_utils
-    "AveragedModel",
-    "SWALR",
     # torch.overrides
     "BaseTorchFunctionMode",
     "TorchFunctionMode",

docs/source/optim.aliases.md

@@ -34,3 +34,111 @@ The following are aliases to their counterparts in ``torch.optim`` in the nested
     Adam
     adam
 ```
+
+```{eval-rst}
+.. automodule:: torch.optim.adamax
+.. currentmodule:: torch.optim.adamax
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    Adamax
+    adamax
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.adamw
+.. currentmodule:: torch.optim.adamw
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    AdamW
+    adamw
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.asgd
+.. currentmodule:: torch.optim.asgd
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    ASGD
+    asgd
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.lbfgs
+.. currentmodule:: torch.optim.lbfgs
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    LBFGS
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.nadam
+.. currentmodule:: torch.optim.nadam
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    NAdam
+    nadam
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.radam
+.. currentmodule:: torch.optim.radam
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    RAdam
+    radam
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.rmsprop
+.. currentmodule:: torch.optim.rmsprop
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    RMSprop
+    rmsprop
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.rprop
+.. currentmodule:: torch.optim.rprop
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    Rprop
+    rprop
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.sgd
+.. currentmodule:: torch.optim.sgd
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    SGD
+    sgd
+```
+
+```{eval-rst}
+.. automodule:: torch.optim.sparse_adam
+.. currentmodule:: torch.optim.sparse_adam
+.. autosummary::
+   :toctree: generated
+   :nosignatures:
+
+    SparseAdam
+```

docs/source/optim.md

@@ -688,18 +688,8 @@ We train the model for a total of 300 epochs and start to collect EMA averages i
 <!-- This module needs to be documented. Adding here in the meantime
 for tracking purposes -->
 ```{eval-rst}
-.. py:module:: torch.optim.adamax
-.. py:module:: torch.optim.adamw
-.. py:module:: torch.optim.asgd
-.. py:module:: torch.optim.lbfgs
 .. py:module:: torch.optim.lr_scheduler
-.. py:module:: torch.optim.nadam
 .. py:module:: torch.optim.optimizer
-.. py:module:: torch.optim.radam
-.. py:module:: torch.optim.rmsprop
-.. py:module:: torch.optim.rprop
-.. py:module:: torch.optim.sgd
-.. py:module:: torch.optim.sparse_adam
 .. py:module:: torch.optim.swa_utils
 ```
 

torch/optim/adagrad.py

@@ -21,7 +21,7 @@ from .optimizer import (
 )
 
 
-__all__: list[str] = ["Adagrad", "adagrad"]
+__all__ = ["Adagrad", "adagrad"]
 
 
 class Adagrad(Optimizer):