Jerry Ma 383d340e88 Small optimization for adam (#12107) ... Summary: Apply weight decay for Adam in-place instead of via copy. Synced offline with soumith , who mentioned that it should be OK. This is also consistent with other optimizers, e.g. eee01731a5/torch/optim/sgd.py (L93) Pull Request resolved: https://github.com/pytorch/pytorch/pull/12107 Reviewed By: soumith Differential Revision: D10071787 Pulled By: jma127 fbshipit-source-id: 5fd7939c79039693b225c44c4c80450923b8d673		2018-09-26 21:43:46 -07:00
..
__init__.py	added AMSgrad optimizer to Adam and SparseAdam (#4034)	2017-12-18 13:24:49 -05:00
adadelta.py	Added parameter range checks for all optimizers (#6000)	2018-03-28 11:22:23 +02:00
adagrad.py	Remove methods that start with an underscore from at::Tensor (#11152)	2018-09-07 11:55:11 -07:00
adam.py	Small optimization for adam (#12107)	2018-09-26 21:43:46 -07:00
adamax.py	Added parameter range checks for all optimizers (#6000)	2018-03-28 11:22:23 +02:00
asgd.py	Added parameter range checks for all optimizers (#6000)	2018-03-28 11:22:23 +02:00
lbfgs.py	Make return uniform in lbfgs step (#7586)	2018-05-16 11:16:46 -04:00
lr_scheduler.py	Changed serialization mechanism of LambdaLR scheduler (#9927)	2018-07-31 19:39:06 -07:00
optimizer.py	migrating deprecated calls without abc module for containers (#11515)	2018-09-13 15:09:22 -07:00
rmsprop.py	Added parameter range checks for all optimizers (#6000)	2018-03-28 11:22:23 +02:00
rprop.py	Added parameter range checks for all optimizers (#6000)	2018-03-28 11:22:23 +02:00
sgd.py	fix SGD lr check (#6244)	2018-04-03 21:29:18 -04:00
sparse_adam.py	Remove methods that start with an underscore from at::Tensor (#11152)	2018-09-07 11:55:11 -07:00