AI RESEARCH
Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
arXiv CS.LG
•
ArXi:2604.08742v1 Announce Type: cross Adam has achieved strong empirical success, but its theory remains incomplete even in the deterministic full-batch setting, largely because adaptive preconditioning and momentum are tightly coupled. In this work, a convergent reformulation of full-batch Adam is developed by combining variable and operator splitting with a curvature-aware gradient correction.