The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the \emph{Grokking Phenomenon}

Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua M. Susskind

Keywords: ptimization, adam, adamw, adaptive optimizers, grokking, training instability, instability, empirical, empirical science of deep learning, double descent

TL;DR: We train neural networks with Adam and cross-entropy loss function. We uncover an anomaly with the behavior of the classification layer's weight norm.

Abstract:

The \emph{grokking phenomenon} reported by Power et al.~\cite{power2021grokking} refers to a regime where a long period of overfitting is followed by a seemingly sudden transition to perfect generalization. In this paper, we attempt to reveal the underpinnings of Grokking via empirical studies. Specifically, we uncover an optimization anomaly plaguing adaptive optimizers at extremely late stages of training, referred to as the \emph{Slingshot Mechanism}. A prominent artifact of the Slingshot Mechanism can be measured by the cyclic phase transitions between stable and unstable training regimes, and can be easily monitored by the cyclic behavior of the norm of the last layers weights. We empirically observe that without explicit regularization, Grokking as reported in \cite{power2021grokking} almost exclusively happens at the onset of \emph{Slingshots}, and is absent without it.
While common and easily reproduced in more general settings, the Slingshot Mechanism does not follow from any known optimization theories that we are aware of, and can be easily overlooked without an in depth examination. Our work points to a surprising and useful inductive bias of adaptive gradient optimizers at late stages of training, calling for a revised theoretical analysis of their origin.