Variational Inference and Deep Learning: A New Synthesis [pdf] (dropbox.com)

This is the PhD thesis of Durk Kingma [1]. Reading this right now; appears to be a well-written introduction to stuff variational autoencoders [2] and ADAM [3].

[1] http://dpkingma.com/

[2] http://arxiv.org/abs/1312.6114

[3] http://arxiv.org/abs/1412.6980