On the Convergence of Adam, Revisited

Abstract

We show that projected Adam for online optimization with arbitrary moment decay parameters ${\beta }_1,{\beta }_2\in [0,1)$ can have average regret bounded away from zero. A similar result of Reddi-Kale-Kumar from 2018 required ${\beta }_1<\sqrt{{\beta }_2}$. Similar to their result, we use a three-periodic sequence of linear functions on $[-1,1]$ with slopes $c,-1,-1$, though we use $c$ slightly larger than $2$. This nonzero average regret result extends to Adam variants such as AdamW, RMSProp, NAdam, Adan, AdaMax, Muon, and to an i.i.d. variant of the three-periodic sequence of slopes for Adam.

26 pages