diff --git a/pytorch_optimizer/__init__.py b/pytorch_optimizer/__init__.py
index f8147013..88a259ed 100644
--- a/pytorch_optimizer/__init__.py
+++ b/pytorch_optimizer/__init__.py
@@ -109,6 +109,7 @@
     Nero,
     NovoGrad,
     PAdam,
+    PCGrad,
     Prodigy,
     QHAdam,
     RAdam,
diff --git a/pytorch_optimizer/optimizer/adopt.py b/pytorch_optimizer/optimizer/adopt.py
index e4706b57..8b7026db 100644
--- a/pytorch_optimizer/optimizer/adopt.py
+++ b/pytorch_optimizer/optimizer/adopt.py
@@ -14,8 +14,6 @@ class ADOPT(BaseOptimizer):
     :param weight_decay: float. weight decay (L2 penalty).
     :param weight_decouple: bool. the optimizer uses decoupled weight decay as in AdamW.
     :param fixed_decay: bool. fix weight decay.
-    :param adanorm: bool. whether to use the AdaNorm variant.
-    :param adam_debias: bool. Only correct the denominator to avoid inflating step sizes early in training.
     :param eps: float. term added to the denominator to improve numerical stability.
     """