Prehistory — From Neural Networks to the TransformerDiederik P. Kingma, Jimmy Ba
Adam: A Method for Stochastic Optimization
Adam: A Method for Stochastic Optimization released on arXiv
Why it matters
The optimizer that later became the de facto standard. Changed the defaults of training recipes
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/1412.6980Added in Week 35, 2026 · See that week