From ffe0409398b4415071c32e2c56af535500fba761 Mon Sep 17 00:00:00 2001
From: Megvii Engine Team <megengine@megvii.com>
Date: Wed, 29 Apr 2020 10:10:17 +0800
Subject: [PATCH] docs(mge/optimizer): refine the docstring of several apis

GitOrigin-RevId: a97fe5b68ace2983a16b747f5b4d73562feb8e9e
---
 python_module/megengine/optimizer/adam.py         | 2 +-
 python_module/megengine/optimizer/internal.py     | 2 +-
 python_module/megengine/optimizer/lr_scheduler.py | 2 +-
 python_module/megengine/optimizer/sgd.py          | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/python_module/megengine/optimizer/adam.py b/python_module/megengine/optimizer/adam.py
index 587ec2f7..6f264d3b 100644
--- a/python_module/megengine/optimizer/adam.py
+++ b/python_module/megengine/optimizer/adam.py
@@ -14,7 +14,7 @@ from .optimizer import Optimizer
 
 
 class Adam(Optimizer):
-    r"""Implements Adam algorithm.
+    r"""Implements Adam algorithm proposed in `"Adam: A Method for Stochastic Optimization" <https://arxiv.org/abs/1412.6980>`_.
 
     :param params: iterable of parameters to optimize or dicts defining
             parameter groups.
diff --git a/python_module/megengine/optimizer/internal.py b/python_module/megengine/optimizer/internal.py
index 7e99b8f4..0483af9a 100644
--- a/python_module/megengine/optimizer/internal.py
+++ b/python_module/megengine/optimizer/internal.py
@@ -21,7 +21,7 @@ def add_update_fastpath(
     beta: Union[Tensor, float, int] = 1.0,
     bias: Union[Tensor, float, int] = 0.0
 ):
-    """a fast-path ONLY used to update parameters in optimzier, since it
+    """a fast-path ONLY used to update parameters in optimizer, since it
     would bypass computing graph and launch dnn/add_update kernel directly,
     it is more efficient than functional/add_update.
     """
diff --git a/python_module/megengine/optimizer/lr_scheduler.py b/python_module/megengine/optimizer/lr_scheduler.py
index 677607c8..7cdb6d9b 100644
--- a/python_module/megengine/optimizer/lr_scheduler.py
+++ b/python_module/megengine/optimizer/lr_scheduler.py
@@ -4,7 +4,7 @@ from .optimizer import Optimizer
 
 
 class LRScheduler(metaclass=ABCMeta):
-    r"""Base class for all lr_schedulers.
+    r"""Base class for all learning rate based schedulers.
 
     :param optimizer: Wrapped optimizer.
     :param current_epoch: The index of current epoch. Default: -1
diff --git a/python_module/megengine/optimizer/sgd.py b/python_module/megengine/optimizer/sgd.py
index 0a24c20a..a1f807b3 100644
--- a/python_module/megengine/optimizer/sgd.py
+++ b/python_module/megengine/optimizer/sgd.py
@@ -17,7 +17,7 @@ class SGD(Optimizer):
     r"""Implements stochastic gradient descent.
 
     Nesterov momentum is based on the formula from
-    `On the importance of initialization and momentum in deep learning`.
+    `"On the importance of initialization and momentum in deep learning" <http://www.cs.toronto.edu/%7Ehinton/absps/momentum.pdf>`_ .
 
     :param params: iterable of parameters to optimize or dicts defining
             parameter groups.