github.com/torch/optim.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2017-11-28	Fixed the link to the Adam research paper	ProGamerGov
	Fixed the link to the, "Adam: A Method for Stochastic Optimization" research paper. This link no longer works: http://arxiv.org/pdf/1412.6980.pdf I and many others involved with machine learning, find it's better to link to the research paper's arXiv page itself, and not directly to the PDF file. This is because it's not easy to get to the research paper's arXiv page, directly from the PDF, but it is easy to get to the PDF from the arXiv page.
2016-07-21	Add learningRateDecay to Adam	Cadene

2016-06-30	Fix bad alignment, trailing spaces and tabs	Alfredo Canziani

2016-06-10	add weight decay support to adam	gcheron

2015-07-30	remove redundant lambda param for adam	Kashif Rasul
	v8 of the paper does not use this parameter
2015-03-06	Update adam.lua	Ajay Talati

2015-03-06	Update adam.lua	Ajay Talati

2015-03-06	Update adam.lua	Ajay Talati

2015-03-06	Update adam.lua	Ajay Talati

2015-03-06	Fixed sign in update rule & default parameters	Ajay Talati
	The sign in the update rule in version 4 (3rd March) of the paper does'nt seem to work? The code works when update to the parameters is positive not negative?
2015-02-26	Fixed optim.adam.	Ivo Danihelka
	The sqrt(v) is now being used instead of pow(v, 2). And I used the default values from the Adam paper: learningRate=2e-4, epsilon=1e-8, lambda=1-1e-8.
2015-02-19	lambda default fix	louissmit

2015-02-03	optim style comments	louissmit

2015-02-03	added adam to init.lua + adam comments	louissmit

2015-02-02	adam	louissmit