https://ai.googleblog.com/2021/03/a-new-lens-on-understanding.html
A New Lens on Understanding Generalization in Deep Learning
Wednesday, March 10, 2021
Hanie Sedghi, Google Research and Preetum Nakkiran, Harvard University
“…we find that models that train quickly on infinite data are the same models that generalize well if they are instead trained on finite data. This connection brings new perspectives on design choices in practice, and lays a roadmap for understanding generalization from a theoretical perspective.”