Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/torch/optim.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/sgd.lua
AgeCommit message (Expand)Author
2016-06-30Fix bad alignment, trailing spaces and tabsAlfredo Canziani
2016-06-03Revert "Fix bug with sgd individual learning rates"revert-113-sgd-lrs-fixSoumith Chintala
2016-06-02Fix bug with individual learning ratesGeoff Pleiss
2015-11-13documentation update for config.learningRates, state.evalCounterArulkumar
2014-11-30copy variables into state params for type castingAysegul Dundar
2014-11-28user either sets wd or wdsAysegul Dundar
2014-11-24more efficient way of state parameters updateAysegul Dundar
2014-11-24weight decay for individual param option addedAysegul Dundar
2013-12-05Better formatting for docstrings in REPLAndreas Fidjeland
2013-12-03Turned documentation into markdown formatAndreas Fidjeland
2013-08-19Allowed to enable Nesterov momentum.Ivo Danihelka
2013-05-24New dampening term.Clement Farabet
2013-05-21CRITICAL: weight decay is finally properly implemented!Clement Farabet
2013-02-19add a 4th parameter to interface to split configuration parameterskoray kavukcuoglu
2012-09-28Updated info / help.Clement Farabet
2012-01-22Merge branch 'lbfgs'Clement Farabet
2012-01-22All debugged L-BFGS implementation.Clement Farabet
2012-01-19Fixed weight decay to scale with learning rate.Clement Farabet
2012-01-18Fixed bugs in SGD and ASGD implementations.Clement Farabet
2011-11-03Added asgd.Clement Farabet
2011-11-03Fixed eval counter for SGFixed eval counter for SGDDClement Farabet
2011-11-03Added first SGD, and orgniazed package.Clement Farabet
    generated by cgit v1.2.3 (git 2.25.1) at 2024-05-17 12:12:14 +0300