1412.6980v8.pdf (arxiv.org)
duchi11a.dvi (jmlr.org)
CSC321 Winter 2014: lecture notes (toronto.edu)
[1212.5701] ADADELTA: An Adaptive Learning Rate Method (arxiv.org)
cs229.stanford.edu/proj2015/054_report.pdf
[1212.5701] ADADELTA: An Adaptive Learning Rate Method (arxiv.org)
lee16.pdf (mlr.press)
1609.04747.pdf (arxiv.org)
