Towards theoretically understanding why SGD generalizes better than ADAM in deep learning

Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven Hoi, E. Weinan

Research output: Contribution to journalConference articlepeer-review

95 Scopus citations

Fingerprint

Dive into the research topics of 'Towards theoretically understanding why SGD generalizes better than ADAM in deep learning'. Together they form a unique fingerprint.

Mathematics

Engineering

Keyphrases